Elamur Research⌕
☰
home / papers / 2025 / Explainability and Interpretability of Multilingual Large Language Models: A Survey

Explainability and Interpretability of Multilingual Large Language Models: A Survey

Paper · 2025 · Lucas Resck, Isabelle Augenstein and Anna Korhonen

Summary

Multilingual large language models (MLLMs) do well on cross-lingual tasks, but it remains unclear how they handle several languages internally, how knowledge moves between languages, and how they deal with scripts, word order or culture-specific bias. Earlier surveys covered either LLM explainability in general or MLLMs without interpretability. The authors present what they describe as the first review focused on this overlap. They gathered literature through keyword searches, including Semantic Scholar, and grouped it along four dimensions: the explanation technique, the multilingual task, the languages studied, and the resources available.

The main conclusion is that most studies take methods built for English and apply them to other languages with little or no adaptation. Low-resource languages, especially African and Asian ones, are poorly served. Work on them rarely goes beyond standard attribution tools.

The survey gives the field a structured map. It also sets out a research agenda: methods designed for multilingual settings, better understanding of cross-lingual transfer, more faithful explanations, and more foundational analyses for under-resourced languages.

Key points

  • The taxonomy covers ten families of methods: probing, latent space analysis, attention analysis, neuron activation, feature attribution, causality & counterfactuals, mechanistic interpretability, natural-language explanations, uncertainty estimation, and visual explanations.
  • Several representative findings are highlighted:
    • Wendler et al. (2024): in intermediate layers, representations of non-English inputs move closer to English.
    • Ma et al. (2021): pruning attention heads tends to improve cross-lingual performance.
    • Hu et al. (2024): reasoning appears to share neurons across languages, while factual knowledge is stored more language-specifically.
  • Research on low-resource languages relies mainly on off-the-shelf tools such as LIME and SHAP. Causal and counterfactual analysis is the notable exception, offering robust methods for such settings.
  • Areas of real methodological novelty include:
    • spontaneous multilingual alignment;
    • language-agnostic latent spaces (e.g., the "Lingua Franca" work by Zeng et al., 2025);
    • probing of lexical tone;
    • artificial languages used as testbeds for transfer;
    • interpretable metrics for MT quality estimation.
  • The paper was published at EMNLP 2025 (pages 20454–20486). The authors state that it is a representative survey rather than a systematic review, so its coverage and categorisation involve some subjectivity.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓University of CambridgeCambridge · United Kingdom256 works · 123,373 citations🎓University of CopenhagenCopenhagen · Denmark116 works · 15,292 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 works

🧭 Topics 3Research subjects and languages the work is about.Language models & pretraining · 3,894 worksMultilingual & cross-lingual NLP · 882 worksInterpretability · 149 works

Cite

Cite as Lucas Resck, Isabelle Augenstein and Anna Korhonen. 2025. Explainability and Interpretability of Multilingual Large Language Models: A Survey. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2025.emnlp-main.1033

@inproceedings{resck2025explainability,
  title = {{Explainability and Interpretability of Multilingual Large Language Models: A Survey}},
  author = {Lucas Resck, Isabelle Augenstein and Anna Korhonen},
  booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing},
  year = {2025},
  doi = {10.18653/v1/2025.emnlp-main.1033},
  url = {https://doi.org/10.18653/v1/2025.emnlp-main.1033}
}

References

242 references, 27 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Maged Abdelaty and Shaimaa Y. Lazem. 2024. Investigating the Robustness of Arabic Offensive Language Transformer-Based Classifiers to Adversarial Attacks. Internet, Multimedia Systems and Applications. find
  2. Badr M. Abdullah, Mohammed Maqsood Shaik, and Dietrich Klakow. 2024. Wave to Interlingua: Analyzing Representations of Multilingual Speech Transformers for Spoken Language Translation. Interspeech. find
  3. Miguel Abreu-Cardenas, Saúl Calderón-Ramírez, and M. Solis. 2023. Uncertainty Estimation for Complex Text Detection in Spanish. 2023 IEEE 5th International Conference on BioInspired Processing (BIP). find
  4. Ehsan Aghazadeh, Mohsen Fayyaz, and Yadollah Yaghoobzadeh. 2022. Metaphors in pre-trained language models: Probing and generalization across datasets and languages. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2037– 2050, D… find
  5. Manex Agirrezabal, Sidsel Boldsen, and Nora Hollenstein. 2023. The hidden folk: Linguistic properties encoded in multilingual contextual character representations. In Proceedings of the Workshop on Computation and Written Language (CAWL 2023), pages 6–13, Toronto, Canada. Association for Computation… find
  6. Saud Althabiti, M. Alsalka, and Eric Atwell. 2024. TA’KEED the First Generative Fact-Checking System for Arabic Claims. Artificial Intelligence and Applications.
  7. Tejaswini Ananthanarayana, Nikunj Kotecha, Priyanshu Srivastava, Lipisha Chaudhary, Nicholas Wilkins, and Ifeoma Nwogu. 2021. Dynamic Cross-Feature Fusion for American Sign Language Translation. IEEE International Conference on Automatic Face & Gesture Recognition. find
  8. Akhilesh Aravapalli, Mounika Marreddy, S. Oota, Radhika Mamidi, and Manish Gupta. 2024. IndicSen-tEval: How Effectively do Multilingual Transformer Models encode Linguistic Properties for Indic Languages? arXiv.org. find
  9. Giuseppe Attanasio, Debora Nozza, Eliana Pastor, and Dirk Hovy. 2022. Benchmarking post-hoc interpretability approaches for transformer-based misogyny detection. In Proceedings of NLP Power! The First Workshop on Efficient Benchmarking in NLP, pages 100–112, Dublin, Ireland. Association for Computat… find
  10. Nadiah A. Baghdadi, Yousry M Abdulazeem, Hanaa ZainEldin, T. A. Farrag, Mansourah Aljohani, Amer Malki, Mahmoud Badawy, and Mostafa A. Elhos-seini. 2024. Toward Robust Arabic Sign Language Recognition via Vision Transformers and Local Interpretable Model-agnostic Explanations Integration. Journal of… find
  11. Nicolas Ballier, Léa Burin, Behnoosh Namdarzadeh, Sara B Ng, Richard Wright, and Jean-Baptiste Yunès. 2024. Probing Whisper Predictions for French, English and Persian Transcriptions. International Conference on Natural Language and Speech Processing. find
  12. Valentin Barriere and Sebastian Cifuentes. 2024a. Are text classifiers xenophobic? a country-oriented bias detection method with least confounding variables. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024),… find
  13. Valentin Barriere and Sebastian Cifuentes. 2024b. A study of nationality bias in names and perplexity using off-the-shelf affect-related tweet classifiers. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 569– 579, Miami, Florida, USA. Association for… find
  14. Hadas Ben-Atya, Naama Gavrielov, Zvi Badash, Gili Focht, Ruth Cytter-Kuint, Talar Hagopian, Dan Turner, and Moti Freiman. 2025. Agent-Based Uncertainty Awareness Improves Automated Radiology Report Labeling with an Open-Source Large Language Model. arXiv preprint.
  15. Matteo Berta, Salvatore Greco, Giuseppe Tipaldo, and Tania Cerquitelli. 2024. Decoding Narratives: Towards a Classification Analysis for Stereotypical Patterns in Italian News Headlines. BigData Congress [Services Society]. find
  16. P. D. Bianco, Oscar Stanchi, F. Quiroga, Franco Ronchetti, and Enzo Ferrante. 2024. SignAttention: On the Interpretability of Transformer Models for Sign Language Translation. arXiv.org. find
  17. Adrien Bibal, Rémi Cardon, David Alfter, Rodrigo Wilkens, Xiaoou Wang, Thomas François, and Patrick Watrin. 2022. Is Attention Explanation? An Introduction to the Debate. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3889–39… find
  18. Alexander Binder, Grégoire Montavon, Sebastian Lapuschkin, Klaus-Robert Müller, and Wojciech Samek. 2016. Layer-Wise Relevance Propagation for Neural Networks with Local Renormalization Layers. In Artificial Neural Networks and Machine Learning – ICANN 2016, volume 9887 of International Conference o… find
  19. Jérémie Bogaert, M. Marneffe, Antonin Descampe, Louis Escouflaire, Cédrick Fairon, and François-Xavier Standaert. 2024. Explanation sensitivity to the randomness of large language models: the case of journalistic text classification. arXiv.org. find
  20. Sidsel Boldsen, Manex Agirrezabal, and Nora Hollenstein. 2022. Interpreting character embeddings with perceptual representations: The case of shape, sound, and color. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6819–6836,… find
  21. Sabri Boughorbel, Md Rizwan Parvez, and Majd Hawasly. 2024. Improving language models trained on translated data with continual pre-training and dictionary learning analysis. In Proceedings of the Second Arabic Natural Language Processing Conference, pages 73–88, Bangkok, Thailand. Association for C…
  22. Stephanie Brandl and Oliver Eberle. 2024. Comparing zero-shot self-explanations with human rationales in multilingual text classification. arXiv.org. find
  23. Stephanie Brandl, Oliver Eberle, Tiago Ribeiro, Anders Søgaard, and Nora Hollenstein. 2024. Evaluating webcam-based gaze data as an alternative for human rationale annotations. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (… find
  24. Giuseppe Buonaiuto, Raffaele Guarasci, Aniello Minutolo, G. Pietro, and M. Esposito. 2024. Quantum Transfer Learning for Acceptability Judgements. Quantum Machine Intelligence. find
  25. R. A. Calix, Jj Ben-Joseph, Nina Lopatina, Ryan Ashley, Mona Gogia, George P. Sieniawski, and Andrea L. Brennen. 2022. Saisiyat Is Where It Is At! Insights Into Backdoors And Debiasing Of Cross Lingual Transformers For Named Entity Recognition. 2022 IEEE International Conference on Big Data (Big Dat… find
  26. Pengfei Cao, Yuheng Chen, Zhuoran Jin, Yubo Chen, Kang Liu, and Jun Zhao. 2024. One Mind, Many Tongues: A Deep Dive into Language-Agnostic Knowledge Neurons in Large Language Models. arXiv.org. find
  27. Terra Blevins, Hila Gonen, and Luke Zettlemoyer. 2022. Analyzing the mono- and cross-lingual pretraining dynamics of multilingual language models. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3575– 3590, Abu Dhabi, United Arab Emirates. Association… find
  28. Tommaso Caselli, Irene Dini, and Felice Dell’Orletta. 2022. How about time? probing a multilingual language model for temporal relations. In Proceedings of the 29th International Conference on Computational Linguistics, pages 3197–3209, Gyeongju, Republic of Korea. International Committee on Computa… find
  29. Jérémie Bogaert, Emmanuel Jean, Cyril de Bodt, and François-Xavier Standaert. 2023. Fine-tuning is not (always) overfitting artifacts. The European Symposium on Artificial Neural Networks. find
  30. Beiduo Chen, Wu Guo, Quan Liu, and Kun Tao. 2022. Feature Aggregation in Zero-Shot Cross-Lingual Transfer Using Multilingual BERT. International Conference on Pattern Recognition. find
  31. Nuo Chen, Ning Wu, Shining Liang, Ming Gong, Linjun Shou, Dongmei Zhang, and Jia Li. 2023. Is Bigger and Deeper Always Better? Probing LLaMA Across Scales and Layers. arXiv.org. find
  32. Yanfang Chen, Ding Chen, Shichao Song, Simin Niu, Hanyu Wang, Zeyun Tang, Feiyu Xiong, and Zhiyu Li. 2024a. HRDE: Retrieval-Augmented Large Language Models for Chinese Health Rumor Detection and Explainability. arXiv.org. find
  33. Yongjian Chen and M. Farrús. 2022. Neural Detection of Cross-lingual Syntactic Knowledge. IberSPEECH Conference. find
  34. Yuyan Chen, Yichen Yuan, Panjun Liu, Dayiheng Liu, Qinghao Guan, Mengfei Guo, Haiming Peng, Bang Liu, Zhixu Li, and Yanghua Xiao. 2024b. Talk Funny! A Large-Scale Humor Response Dataset with Chain-of-Humor Interpretation. AAAI Conference on Artificial Intelligence. find
  35. Long Cheng, Qihao Shao, Christine Zhao, Sheng Bi, and Gina-Anne Levow. 2024. TEII: Think, explain, interact and iterate with large language models to solve cross-lingual emotion detection. In Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Anal… find
  36. Ahmadul Karim Chowdhury, Saidur Rahman Sujon, Md. Shirajus Salekin Shafi, Tasin Ahmmad, Sifat Ahmed, Khan Md Hasib, and Faisal Muhammad Shah. 2024. Harnessing Large Language Models Over Transformer Models for Detecting Bengali Depressive Social Media Text: A Comprehensive Study. Natural Language Pro… find
  37. Simone Conia and Roberto Navigli. 2022. Probing for predicate argument structures in pretrained language models. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4622–4632, Dublin, Ireland. Association for Computational Linguis… find
  38. Yiming Cui, Ting Liu, Wanxiang Che, Zhigang Chen, and Shijin Wang. 2022. Teaching Machines to Read, Answer and Explain. IEEE/ACM Transactions on Audio Speech and Language Processing. find
  39. Yiming Cui, Wei-Nan Zhang, Wanxiang Che, Ting Liu, Zhigang Chen, and Shijin Wang. 2021. Multilingual Multi-Aspect Explainability Analyses on Machine Reading Comprehension Models. arXiv preprint. find
  40. Thao Anh Dang, Limor Raviv, and Lukas Galke. 2024. Tokenization and Morphology in Multilingual Language Models: A Comparative Analysis of mT5 and ByT5. arXiv.org. find
  41. Ant’on de la Fuente and Dan Jurafsky. 2024. A layer-wise analysis of Mandarin and English suprasegmentals in SSL speech models. Interspeech. find
  42. Loic De Langhe, Orphee De Clercq, and Veronique Hoste. 2023. What does BERT actually learn about event coreference? probing structural information in a fine-tuned Dutch language model. In Proceedings of the Fourth Workshop on Insights from Negative Results in NLP, pages 103–108, Dubrovnik, Croatia.… find
  43. Darshan Deshpande, Selvan Sunitha Ravi, Sky CH-Wang, B. Mielczarek, Anand Kannappan, and Rebecca Qian. 2024. GLIDER: Grading LLM Interactions and Decisions using Explainable Ranking. arXiv.org. find
  44. Clément Dumas, Chris Wendler, Veniamin Veselovsky, Giovanni Monea, and Robert West. 2025. Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics…
  45. Sebastian-Vasile Echim, Razvan-Alexandru Smadu, and Dumitru-Clementin Cercel. 2024. Benchmarking Adversarial Robustness in Speech Emotion Recognition: Insights into Low-Resource Romanian and German Languages. European Conference on Artificial Intelligence. find
  46. Bojan Evkoski and Senja Pollak. 2023. XAI in Computational Linguistics: Understanding Political Leanings in the Slovenian Parliament. arXiv preprint. find
  47. Jiahai Feng, Stuart Russell, and Jacob Steinhardt. 2024. Monitoring Latent World States in Language Models with Propositional Probes. arXiv.org. find
  48. Javier Ferrando and Marta R. Costa-jussà. 2024. On the similarity of circuits across languages: a case study on the subject-verb agreement task. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 10115–10125, Miami, Florida, USA. Association for Computational Linguistics… find
  49. Javier Ferrando, Gerard I. Gállego, Belen Alastruey, Carlos Escolano, and Marta R. Costa-jussà. 2022. Towards opening the black box of neural machine translation: Source and target interpretations of the transformer. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Proc… find
  50. Javier Ferrando and Elena Voita. 2024. Information flow routes: Automatically interpreting language models at scale. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 17432–17445, Miami, Florida, USA. Association for Computational Linguistics.
  51. Y. Fung, Tuhin Chakraborty, Hao Guo, Owen Rambow, S. Muresan, and Heng Ji. 2022. NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly. Conference on Empirical Methods in Natural Language Processing. find
  52. Lance Calvin Lim Gamboa and Mark Lee. 2024. A Novel Interpretability Metric for Explaining Bias in Language Models: Applications on Multilingual Models from Southeast Asia. arXiv.org. find
  53. Rouzbeh Ghasemi and S. Momtazi. 2023. How a Deep Contextualized Representation and Attention Mechanism Justifies Explainable Cross-Lingual Sentiment Analysis. ACM Trans. Asian Low Resour. Lang. Inf. Process. find
  54. Sai Gopinath and Joselyn Rodriguez. 2024. Probing self-attention in self-supervised speech models for cross-linguistic differences. arXiv.org. find
  55. R. Grosse, Juhan Bae, Cem Anil, Nelson Elhage, Alex Tamkin, Amirhossein Tajdini, Benoit Steiner, Dustin Li, Esin Durmus, Ethan Perez, Evan Hubinger, Kamil.e Lukovsiut.e, Karina Nguyen, Nicholas Joseph, Sam McCandlish, Jared Kaplan, and Sam Bowman. 2023. Studying Large Language Model Generalization w…
  56. Muzhe Guo, Muhao Guo, Juntao Su, Junyu Chen, Jiaqian Yu, Jiaqi Wang, Hongfei Du, Parmanand Sahu, Ashwin Assysh Sharma, and Fang Jin. 2024. Bayesian Iterative Prediction and Lexical-based Interpretation for Disturbed Chinese Sentence Pair Matching. The Web Conference. find
  57. Wataru Hashimoto, Hidetaka Kamigaito, and Taro Watanabe. 2024. Are data augmentation methods in named entity recognition applicable for uncertainty estimation? In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 18852–18867, Miami, Florida, USA. Associati… find
  58. Ehtesham Hashmi, Muhammad Mudassar Yamin, Shariq Imran, Sule YAYILGAN YILDIRIM, and Mohib Ullah. 2024a. Enhancing Misogyny Detection in Bilingual Texts Using FastText and Explainable AI. 2024 International Conference on Engineering & Computing Technologies (ICECT). find
  59. Ehtesham Hashmi, Sule YAYILGAN YILDIRIM, Ibrahim A. Hameed, M. Yamin, Mohib Ullah, and Mohamed Abomhara. 2024b. Enhancing Multilingual Hate Speech Detection: From Language-Specific Insights to Cross-Linguistic Integration. IEEE Access. find
  60. Linyang He, Ercong Nie, Helmut Schmid, Hinrich Schutze, N. Mesgarani, and Jonathan R. Brennan. 2024. Large Language Models as Neurolinguistic Subjects: Identifying Internal Representations for Form and Meaning. arXiv.org. find
  61. Musashi Hinck, Carolin Holtermann, Matthew Lyle Olson, Florian Schneider, Sungduk Yu, Anahita Bhiwandiwalla, Anne Lauscher, Shao-Yen Tseng, and Vasudev Lal. 2024. Why do LLaVA vision-language models reply to images in English? In Findings of the Association for Computational Linguistics: EMNLP 2024,…
  62. MD. Mithun Hossain, Md Shakil Hossain, Md Shakhawat Hossain, M. F. Mridha, Mejdl S. Safran, and Sultan Alfarhood. 2024a. TransNet: Deep Attentional Hybrid Transformer for Arabic Posts Classification. IEEE Access. find
  63. MD. Mithun Hossain, Md Shakil Hossain, Mejdl S. Safran, Sultan Alfarhood, Meshal Alfarhood, and M. F. Mridha. 2024b. A Hybrid Attention-Based Transformer Model for Arabic News Classification Using Text Embedding and Deep Learning. IEEE Access. find
  64. Peng Hu, Sizhe Liu, Changjiang Gao, Xin Huang, Xue Han, Junlan Feng, Chao Deng, and Shujian Huang. 2024. Large Language Models Are Cross-Lingual Knowledge-Free Reasoners. arXiv.org. find
  65. Zhihong Huang, Longyue Wang, Siyou Liu, and Derek F. Wong. 2023. How Does Pretraining Improve Discourse-Aware Translation? Interspeech. find
  66. Benjamin Icard, Evangelia Zve, Lila Sainero, Alice Breton, and Jean-Gabriel Ganascia. 2025. Embedding style beyond topics: Analyzing dispersion effects across different language models. In Proceedings of the 31st International Conference on Computational Linguistics, pages 3511–3522, Abu Dhabi, UAE.… find
  67. Verena Irrgang, Veronika Solopova, Steffen Zeiler, Robert M. Nickel, and D. Kolossa. 2024. Features and Detectability of German Texts Generated with Large Language Models. Conference on Natural Language Processing. find
  68. Ai Ishii, Naoya Inoue, Hisami Suzuki, and Satoshi Sekine. 2024. JEMHopQA: Dataset for Japanese explainable multi-hop question answering. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 9515– 9525, Tor… find
  69. Saiful Islam, Md Jabed Hosen, Fowzia Rahman Taznin, Naznin Sultana, Md. Injamul Haque, and Shakil Rana. 2024. An Efficient Framework for Transliteration Sentence Identification of Low Resource Languages Using Hybrid BERT-BiGRU. International Conference on Computing Communication and Networking Techn… find
  70. Yalong Jia, Zhenghui Ou, and Yang Yang. 2022. SPDB innovation lab at SemEval-2022 task 10: A novel end-to-end structured sentiment analysis model based on the ERNIE-M. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 1401–1405, Seattle, United States. As… find
  71. Cong Jiang and Xiaolei Yang. 2023. Legal Syllogism Prompting: Teaching Large Language Models for Legal Judgment Prediction. International Conference on Artificial Intelligence and Law. find
  72. Xinke Jiang, Ruizhe Zhang, Yongxin Xu, Rihong Qiu, Yue Fang, Zhiyuan Wang, Jinyi Tang, Hongxin Ding, Xu Chu, Junfeng Zhao, and Yasha Wang. 2023. HyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs Responses. arXiv preprint. find
  73. Rasmus Jørgensen, Fiammetta Caccavale, Christian Igel, and Anders Søgaard. 2022. Are multilingual sentiment models equally right for the right reasons? In Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, pages 131–141, Abu Dhabi, United Arab Emirat… find
  74. Wagner, Lucy Lu Wang, Chris Wilhelm, Caroline Wu, Jiangjiang Yang, Angele Zamarron, Madeleine Van Zuylen, and Daniel S. Weld. 2025. The Semantic Scholar Open Data Platform. arXiv preprint. ArXiv:2301.10140 [cs]. find
  75. Belinda Marion Kobusingye, A. Dorothy, J. Nakatumba-Nabende, and Ggaliwango Marvin. 2023. Explainable Machine Translation for Intelligent E-Learning of Social Studies. 2023 7th International Conference on Trends in Electronics and Informatics (ICOEI). find
  76. Tasnim Kabir and Marine Carpuat. 2021. The UMD submission to the explainable MT quality estimation shared task: Combining explanation models with sequence labeling. In Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems, pages 230–237, Punta Cana, Dominican Republic. Associat… find
  77. Takeshi Kojima, Itsuki Okimura, Yusuke Iwasawa, Hitomi Yanaka, and Yutaka Matsuo. 2024. On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons. In Proceedings of the 2024 Conference of the North American Chapter of the Association…
  78. Migyeong Kang, Goun Choi, Hyolim Jeon, Ji Hyun An, Daejin Choi, and Jinyoung Han. 2024. CURE: Context- and uncertainty-aware mental disorder detection. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 17924–17940, Miami, Florida, USA. Association for C… find
  79. Anastasia Kozlova, Albina Akhmetgareeva, Aigul Khanova, Semen Kudriavtsev, and Alena Fenogenova. 2024. Transformer attention vs human attention in anaphora resolution. In Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics, pages 109–122, Bangkok, Thailand. Association fo… find
  80. Md. Rezaul Karim, Sumon Dey, and Bharathi Raja Chakravarthi. 2020. DeepHateExplainer: Explainable Hate Speech Detection in Under-resourced Bengali Language. International Conference on Data Science and Advanced Analytics. find
  81. Anisia Katinskaia and Roman Yangarber. 2024. Probing the category of verbal aspect in transformer language models. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 3347–3366, Mexico City, Mexico. Association for Computational Linguistics. find
  82. Ayush Kaushal and Kyle Mahowald. 2022. What do tokens know about their characters and how do they know it? In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2487–2507, Seattle, United States. Assoc… find
  83. Rodney Kinney, Chloe Anastasiades, Russell Authur, Iz Beltagy, Jonathan Bragg, Alexandra Buraczynski, Isabel Cachola, Stefan Candra, Yoganand Chandrasekhar, Arman Cohan, Miles Crawford, Doug Downey, Jason Dunkelberger, Oren Etzioni, Rob Evans, Sergey Feldman, Joseph Gorney, David Graham, Fangzhou Hu… find
  84. Simon Kurz, Jian-Jia Chen, Lucie Flek, and Zhixue Zhao. 2024. Investigating Language-Specific Calibration For Pruning Multilingual Large Language Models. arXiv preprint. find
  85. Viet Lai, Chien Nguyen, Nghia Ngo, Thuat Nguyen, Franck Dernoncourt, Ryan Rossi, and Thien Nguyen. 2023. Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback. In Proceedings of the 2023 Conference on Empirical Methods in Natural Languag…
  86. Michael Lan, Philip Torr, and Fazl Barez. 2024. Towards interpretable sequence continuation: Analyzing shared circuits in large language models. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 12576– 12601, Miami, Florida, USA. Association for Computa… find
  87. Anne Lauscher, Federico Bianchi, Samuel R. Bowman, and Dirk Hovy. 2022. SocioProbe: What, when, and where language models learn about sociodemographics. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 7901–7918, Abu Dhabi, United Arab Emirates. Associ… find
  88. You-Qian Lee, Ching-Tai Chen, Chien-Chang Chen, Chung-Hong Lee, Pei-Tsz Chen, Chi-Shin Wu, and Hong-Jie Dai. 2023. Unlocking the Secrets Behind Advanced Artificial Intelligence Language Models in Deidentifying Chinese-English Mixed Clinical Text: Development and Validation Study. Journal of Medical… find
  89. Yunseung Lee and Daehee Han. 2024. KorSmishing explainer: A Korean-centric LLM-based framework for smishing detection and explanation generation. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 642–656, Miami, Florida, US. Association… find
  90. Bingzhi Li, Guillaume Wisniewski, and Benoit Crabbé. 2022. How distributed are distributed representations? an observation on the locality of syntactic information in verb agreement tasks. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Pap… find
  91. Bingzhi Li, Guillaume Wisniewski, and Benoît Crabbé. 2023a. Assessing the capacity of transformer to abstract syntactic representations: A contrastive analysis based on long-distance agreement. Transactions of the Association for Computational Linguistics, 11:18–33. find
  92. Daoyang Li, Mingyu Jin, Qingcheng Zeng, Haiyan Zhao, and Mengnan Du. 2024a. Exploring Multilingual Probing in Large Language Models: A Cross-Language Analysis. arXiv.org. find
  93. Xiaochen Li, Zheng Xin Yong, and Stephen Bach. 2024c. Preference tuning for toxicity mitigation generalizes across languages. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 13422–13440, Miami, Florida, USA. Association for Computational Linguistics. find
  94. Sheng Liang, Philipp Dufter, and Hinrich Schütze. 2020. Monolingual and multilingual reduction of gender bias in contextualized representations. In Proceedings of the 28th International Conference on Computational Linguistics, pages 5082–5093, Barcelona, Spain (Online). International Committee on Co… find
  95. Yu-Ting Lin, Yuan-Xiang Deng, Chu-Lin Tsai, Chien-Hua Huang, and Lijuan Fu. 2024. Interpretable Deep Learning System for Identifying Critical Patients Through the Prediction of Triage Level, Hospitalization, and Length of Stay: Prospective Study. JMIR Medical Informatics. find
  96. Chen Cecilia Liu, Iryna Gurevych, and Anna Korhonen. 2024a. Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art. arXiv preprint. ArXiv:2406.03930.
  97. Fan Liu, Yue Feng, Zhao Xu, Lixin Su, Xinyu Ma, Dawei Yin, and Hao Liu. 2024b. JAIL-JUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework. arXiv.org. find
  98. Qi Liu, Matt Kusner, and Phil Blunsom. 2021. Counterfactual data augmentation for neural machine translation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 187–197, Online. Association for Comp… find
  99. Shuo Liu, J. Keung, Zhen Yang, Fang Liu, Qilin Zhou, and Yihan Liao. 2024c. Delving into Parameter-Efficient Fine-Tuning in Code Change Learning: An Empirical Study. IEEE International Conference on Software Analysis, Evolution, and Reengineering. find
  100. Dongfang Li, Jindi Yu, Baotian Hu, Zhenran Xu, and Min Zhang. 2023b. ExplainCPE: A free-text explanation benchmark of Chinese pharmacist examination. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 1922–1940, Singapore. Association for Computational Linguistics. find
  101. Weize Liu, Yinlong Xu, Hongxia Xu, Jintai Chen, Xuming Hu, and Jian Wu. 2024d. Unraveling Babel: Exploring multilingual activation patterns of LLMs and their applications. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 11855–11881, Miami, Florida, US… find
  102. Jiahong Li, Yiyuan Chen, Yichi Wang, Yiqiang Ye, Min Sun, Haopan Ren, Weibin Cheng, and Haodi Zhang. 2023c. Interpretable Pulmonary Disease Diagnosis with Graph Neural Network and Counterfactual Explanations. 2023 2nd International Conference on Sensing, Measurement, Communication and Internet of Th… find
  103. Antoine Louis, G. van Dijck, and Gerasimos Spanakis. 2023. Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models. AAAI Conference on Artificial Intelligence.
  104. Jie Li, Yi Liu, Chongyang Liu, Ling Shi, Xiaoning Ren, Yaowen Zheng, Yang Liu, and Yinxing Xue. 2024b. A Cross-Language Investigation into Jailbreak Attacks in Large Language Models. arXiv.org. find
  105. Qingyu Lu, Baopu Qiu, Liang Ding, Kanjian Zhang, Tom Kocmi, and Dacheng Tao. 2024. Error analysis prompting enables human-like translation evaluation in large language models. In Findings of the Association for Computational Linguistics: ACL 2024, pages 8801–8816, Bangkok, Thailand. Association for…
  106. Qiuhao Lu, Sairam Gurajada, Prithviraj Sen, Lucian Popa, Dejing Dou, and Thien Nguyen. 2022. Cross-lingual short-text entity linking: Generating features for neuro-symbolic methods. In Proceedings of the Fourth Workshop on Data Science with Human-in-the-Loop (Language Advances), pages 8–14, Abu Dhab… find
  107. Scott M Lundberg and Su-In Lee. 2017. A Unified Approach to Interpreting Model Predictions. In Advances in Neural Information Processing Systems 30 (NIPS 2017), volume 30. Curran Associates, Inc.
  108. Haoyan Luo and Lucia Specia. 2024. From Understanding to Utilization: A Survey on Explainability for Large Language Models. arXiv preprint. ArXiv:2401.12874 [cs]. — [arXiv:2401.12874](https://arxiv.org/abs/2401.12874) find
  109. Weicheng Ma, Kai Zhang, Renze Lou, Lili Wang, and Soroush Vosoughi. 2021. Contributions of transformer attention heads in multi- and cross-lingual tasks. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural… find
  110. Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing Data using t-SNE. Journal of Machine Learning Research, 9(86):2579–2605. find
  111. K. Mabokela, Mpho Primus, and Turgay Çelik. 2024. Explainable Pre-Trained Language Models for Sentiment Analysis in Low-Resourced Languages. Big Data and Cognitive Computing. find
  112. VÍıtor Machado, C. Bom, Kary Ocaña, R. Terra, and Miriam Chaves. 2022. Using Deep Learning Transformer Networks to Identify Symptoms Associated with COVID-19 on Twitter. Notas técnicas. find
  113. Daniil Maksymenko and Oleskii Turuta. 2024. Interpretable Conversation Routing via the Latent Embeddings Approach. Computation. find
  114. Melusi Malinga, Isaac Lupanda, Mike Wa Nkongolo, and Jacobus Philippus van Deventer. 2024. A Multilingual Sentiment Lexicon for Low-Resource Language Translation using Large Languages Models and Explainable AI. arXiv.org. find
  115. Mamta Mamta, Zishan Ahmad, and Asif Ekbal. 2023. Elevating code-mixed text handling through auditory information of words. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 15918–15932, Singapore. Association for Computational Linguistics. find
  116. D. Mareček, H. Çelikkanat, Miikka Silfverberg, Vinit Ravishankar, and J. Tiedemann. 2020. Are Multilingual Neural Machine Translation Models Better at Capturing Linguistic Features? Prague Bulletin of Mathematical Linguistics. find
  117. Leland McInnes, John Healy, Nathaniel Saul, and Lukas Großberger. 2018. UMAP: Uniform Manifold Approximation and Projection. Journal of Open Source Software, 3(29):861. find
  118. Tim Metzler, P. Plöger, and Jörn Hees. 2024. Computer-Assisted Short Answer Grading Using Large Language Models and Rubrics. Jahrestagung der Gesellschaft für Informatik. find
  119. Alessio Miaschi, Chiara Alzetta, D. Brunato, F. Dell’Orletta, and Giulia Venturi. 2023a. Testing the Effectiveness of the Diagnostic Probing Paradigm on Italian Treebanks. Inf. find
  120. Alessio Miaschi, D. Brunato, F. Dell’Orletta, and Giulia Venturi. 2023b. On Robustness and Sensitivity of a Neural Language Model: A Case Study on Italian L1 Learner Errors. IEEE/ACM Transactions on Audio Speech and Language Processing. find
  121. Alessio Miaschi, Gabriele Sarti, D. Brunato, F. Dell’Orletta, and Giulia Venturi. 2022. Probing Linguistic Knowledge in Italian Neural Language Models across Language Varieties. Italian Journal of Computational Linguistics. find
  122. Anamaria-Monica Migea, Vlad-Andrei Negru, Sebastian-Antonio Toma, C. Lemnaru, and R. Potolea. 2024. Cook Smarter Not Harder: Enhancing Learning Capacity in Smart Ovens with Supplementary Data. International Conference on Computational Photography. find
  123. Vladislav Mikhailov, Oleg Serikov, and Ekaterina Artemova. 2021a. Morph call: Probing morphosyntactic content of multilingual transformers. In Proceedings of the Third Workshop on Computational Typology and Multilingual NLP, pages 97–121, Online. Association for Computational Linguistics. find
  124. Vladislav Mikhailov, Ekaterina Taktasheva, Elina Sigdel, and Ekaterina Artemova. 2021b. RuSentEval: Linguistic source, encoder force! In Proceedings of the 8th Workshop on Balto-Slavic Natural Language Processing, pages 43–65, Kiyv, Ukraine. Association for Computational Linguistics. find
  125. Hosein Mohebbi, Grzegorz Chrupała, Willem Zuidema, and Afra Alishahi. 2023. Homophone disambiguation reveals patterns of context mixing in speech transformers. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 8249–8260, Singapore. Association for Compu… find
  126. Yongyu Mu, Peinan Feng, Zhiquan Cao, Yuzhang Wu, Bei Li, Chenglong Wang, Tong Xiao, Kai Song, Tongran Liu, Chunliang Zhang, and Jingbo Zhu. 2024. Revealing the Parallel Multilingual Learning within Large Language Models. arXiv preprint. find
  127. Aaron Mueller, Yu Xia, and Tal Linzen. 2022. Causal analysis of syntactic agreement neurons in multilingual language models. In Proceedings of the 26th Conference on Computational Natural Language Learning (CoNLL), pages 95–109, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational… find
  128. A. Munthuli, P. Pooprasert, N. Klangpornkun, P. Phien-phanich, C. Onsuwan, Kankamol Jaisin, Keerati Pat-tanaseri, Juthawadee Lortrakul, and C. Tantibundhit. 2023. Classification and analysis of text transcription from Thai depression assessment tasks among patients with depression. PLoS ONE. find
  129. Ahmad Mustafa, Saja Nakhleh, R. Irsheidat, and R. Al-ruosan. 2024. Interpreting Arabic Transformer Models: A Study on XAI Interpretability for Quranic Semantic Search Models. Jordanian Journal of Computers and Information Technology. find
  130. Nikolaos Mylonas, Nikolaos Stylianou, T. Tsikrika, S. Vrochidis, and I. Kompatsiaris. 2024. A Multi-Task Text Classification Pipeline with Natural Language Explanations: A User-Centric Evaluation in Sentiment Analysis and Offensive Language Identification in Greek Tweets. arXiv.org. find
  131. Aleksandra Mysiak and Jacek Cyranka. 2023. Is German secretly a Slavic language? what BERT probing can tell us about language groups. In Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023), pages 86–93, Dubrovnik, Croatia. Association for Computational Linguis… find
  132. Inez Okulska and Emilia Wiśnios. 2023. Towards Harmful Erotic Content Detection through Coreference-Driven Contextual Analysis. CRAC. find
  133. Hilário Oliveira, Rafael Ferreira Mello, Bruno Alexandre Barreiros Rosa, Mladen Raković, Péricles B. C. Miranda, T. Cordeiro, Seiji Isotani, I. Bittencourt, and D. Gašević. 2023. Towards explainable prediction of essay cohesion in Portuguese and English. International Conference on Learning Analyt… find
  134. OpenAI, Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, Red Avila, Igor Babuschkin, Suchir Balaji, Valerie Balcom, Paul Baltescu, Haiming Bao, Mohammad Bavarian, Jeff Belgum, Irwan Bello, Ja… — GPT-4 Technical Report
  135. Asli Umay Ozturk, R. Çekinel, and Pinar Senkul. 2024. Make Satire Boring Again: Reducing Stylistic Bias of Satirical Corpus by Utilizing Generative LLMs. arXiv.org. find
  136. Pia Pachinger, Janis Goldzycher, Anna Planitzer, Wojciech Kusa, Allan Hanbury, and Julia Neidhardt. 2024. AustroTox: A dataset for target-based Austrian German offensive language detection. In Findings of the Association for Computational Linguistics: ACL 2024, pages 11990–12001, Bangkok, Thailand.… find
  137. Dojun Park and Sebastian Padó. 2024. Multi-dimensional machine translation evaluation: Model evaluation and resource for Korean. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 11723–11744, Torino, It… find
  138. D.E. Pashchenko, E. Razova, A. Kotelnikova, S. Vychegzhanin, and E. V. Kotelnikov. 2022. Interpretation of Language Models Attention Matrices in Texts Sentiment Analysis. 2022 VIII International Conference on Information Technology and Nanotechnology (ITNT). find
  139. Gal Patel, Leshem Choshen, and Omri Abend. 2022. On neurons invariant to sentence structural changes in neural machine translation. In Proceedings of the 26th Conference on Computational Natural Language Learning (CoNLL), pages 194–212, Abu Dhabi, United Arab Emirates (Hybrid). Association for Compu… find
  140. Rajaswa Patil, Jasleen Dhillon, Siddhant Mahurkar, Saumitra Kulkarni, Manav Malhotra, and Veeky Baths. 2021. Vyākarana: A colorless green benchmark for syntactic evaluation in indic languages. In Proceedings of the 1st Workshop on Multilingual Representation Learning, pages 153–165, Punta Cana, Dom… find
  141. Siddhesh Pawar, Junyeong Park, Jiho Jin, Arnav Arora, Junho Myung, Srishti Yadav, Faiz Ghifari Haznitrama, Inhwa Song, Alice Oh, and Isabelle Augenstein. 2024. Survey of Cultural Awareness in Language Models: Text and Beyond. arXiv preprint. ArXiv:2411.00860.
  142. Telmo Pires, Eva Schlinger, and Dan Garrette. 2019. How multilingual is multilingual BERT? In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4996–5001, Florence, Italy. Association for Computational Linguistics.
  143. Luca Putelli, A. Gerevini, A. Lavelli, T. Mehmood, and I. Serina. 2022. On the Behaviour of BERT’s Attention for the Classification of Medical Reports. XAI.it@AI*IA. find
  144. Libo Qin, Qiguang Chen, Yuhang Zhou, Zhi Chen, Yinghui Li, Lizi Liao, Min Li, Wanxiang Che, and Philip S. Yu. 2024. Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers. arXiv preprint. ArXiv:2404.04925 [cs].
  145. Lucia Quirke, Lovis Heindrich, Wes Gurnee, and Neel Nanda. 2023. Training Dynamics of Contextual N-Grams in Language Models. arXiv.org. find
  146. Azzam Radman, Mohammed Atros, and Rehab Duwairi. 2023. Neural Arabic singular-to-plural conversion using a pretrained Character-BERT and a fused transformer. Natural Language Engineering. find
  147. Rashedur M. Rahman, Gw’enol’e Lecorv’e, and Nicolas B’echet. 2023. Age Recommendation from Texts and Sentences for Children. arXiv.org. find
  148. Mirco Ramo, G. Silvestre, and F. Balado. 2023. Small, Multilingual, Explainable Transformers for Online Handwriting Decoding. Irish Signals and Systems Conference. find
  149. Juncang Rao and Yanshan He. 2024. Research on Automated Scoring Method for HSK Essays with Hybrid Features. International Conference on Asian Language Processing. find
  150. Manikandan Ravikiran and Bharathi Raja Chakravarthi. 2022. Zero-shot code-mixed offensive span identification through rationale extraction. In Proceedings of the Second Workshop on Speech and Language Technologies for Dravidian Languages, pages 240– 247, Dublin, Ireland. Association for Computationa… find
  151. Ryokan Ri and Yoshimasa Tsuruoka. 2022. Pretraining with artificial language: Studying transferable knowledge in language models. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7302– 7315, Dublin, Ireland. Association for Com… find
  152. Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2016. "Why Should I Trust You?": Explaining the Predictions of Any Classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’16, pages 1135–1144, New York, NY, USA. Association for C…
  153. Phillip Richter-Pechanski, Philipp Wiesenbach, Dominic M. Schwab, Christina Kiriakou, Nicolas Geis, Christoph Dieterich, and Anette Frank. 2024. Clinical information extraction for Low-resource languages with Few-shot learning using Pre-trained language models and Prompting. Natural Language Process… find
  154. M. T. Rietberg, Van Bach Nguyen, J. Geerdink, Onno Vijlbrief, and Christin Seifert. 2023. Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models. Diagnostics. find
  155. Sandy Ritchie, Daan van Esch, Uche Okonkwo, Shikhar Vashishth, and Emily Drummond. 2024. LinguaMeta: Unified Metadata for Thousands of Languages. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 10530–… find
  156. Ana Carolina Rodrigues and R. Marcacini. 2022. Sentence Similarity Recognition in Portuguese from Multiple Embedding Models. International Conference on Machine Learning and Applications. find
  157. Samuel Rönnqvist, Jenna Kanerva, Tapio Salakoski, and Filip Ginter. 2019. Is multilingual BERT fluent in language generation? In Proceedings of the First NLPL Workshop on Deep Learning for Natural Language Processing, pages 29–36, Turku, Finland. Linköping University Electronic Press. find
  158. Rishiraj Saha Roy, Joel Schlotthauer, Chris Hinze, Andreas Foltyn, Luzian Hahn, and Fabian Kuech. 2024. Evidence Contextualization and Counterfactual Attribution for Conversational QA over Heterogeneous Data with RAG Systems. arXiv.org. find
  159. Abdulwahab Sahyoun and Shady Shehata. 2023. AraDi-aWER: An explainable metric for dialectical Arabic ASR. In Proceedings of the Second Workshop on NLP Applications to Field Linguistics, pages 64–73, Dubrovnik, Croatia. Association for Computational Linguistics. find
  160. Oleg Serikov, Vitaly Protasov, Ekaterina Voloshina, Viktoria Knyazkova, and Tatiana Shavrina. 2022. Universal and independent: Multilingual probing framework for exhaustive model interpretation and evaluation. In Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Netw… find
  161. Sheikh Shafayat, Dongkeun Yoon, Woori Jang, Jiwoo Choi, Alice Oh, and Seohyon Jung. 2024. A 2-step Framework for Automated Literary Translation Evaluation: Its Promises and Pitfalls. arXiv.org. find
  162. Naomi Shapiro, Amandalynne Paullada, and Shane Steinert-Threlkeld. 2021. A multilabel approach to morphosyntactic probing. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4486–4524, Punta Cana, Dominican Republic. Association for Computational Linguistics. find
  163. Gaofei Shen, Michaela Watkins, Afra Alishahi, Arianna Bisazza, and Grzegorz Chrupała. 2024. Encoding of lexical tone in self-supervised models of spoken language. arXiv preprint. find
  164. Ya-Ming Shen, Lijie Wang, Ying Chen, Xinyan Xiao, Jing Liu, and Hua Wu. 2022. An Interpretability Evaluation Benchmark for Pre-trained Language Models. arXiv.org. find
  165. J. A. Siddiqui, S. Yuhaniz, Ghulam Mujtaba, Safdar Ali Soomro, and Zafar Ali Mahar. 2024. Fine-Grained Multilingual Hate Speech Detection Using Explainable AI and Transformers. IEEE Access. find
  166. Anant Singh and Akshat Gupta. 2023. Decoding Emotions: A comprehensive Multilingual Study of Speech Models for Speech Emotion Recognition. arXiv.org. find
  167. Tooba Sohail, Atiqa Aiman, Ehtesham Hashmi, A. Imran, Sher Muhammad Daudpota, and Sule YAYIL-GAN YILDIRIM. 2024. Hate Speech Detection in Code-Mixed Datasets Using Pretrained Embeddings and Transformers. International Conference on Frontiers of Information Technology. find
  168. Guijin Son, Dongkeun Yoon, Juyoung Suk, Javier Aula-Blasco, Mano Aslan, Vu Trong Kim, Shayekh Bin Islam, Jaume Prats-Cristià, Lucía Tormo-Bañuelos, and Seungone Kim. 2024. MM-Eval: A Multilingual Meta-Evaluation Benchmark for LLM-as-a-Judge and Reward Models. arXiv preprint. ArXiv:2410.17578. — [arXiv:2410.17578](https://arxiv.org/abs/2410.17578) find
  169. Anirudh Srinivasan, Venkata S Govindarajan, and Kyle Mahowald. 2023. Counterfactually Probing Language Identity in Multilingual Models. MRL. find
  170. Felix Stahlberg, Danielle Saunders, and Bill Byrne. 2018. An operation sequence model for explainable neural machine translation. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 175–186, Brussels, Belgium. Association for Computational… find
  171. Giulio Starace, Konstantinos Papakostas, Rochelle Choenni, Apostolos Panagiotopoulos, Matteo Rosati, Alina Leidinger, and Ekaterina Shutova. 2023. Probing LLMs for joint encoding of linguistic categories. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 7158–7179, Sing… find
  172. Victor Steinborn, Philipp Dufter, Haris Jabbar, and Hinrich Schuetze. 2022. An information-theoretic approach and dataset for probing gender stereotypes in multilingual masked language models. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 921–932, Seattle, United St… find
  173. Marek Strong, Rami Aly, and Andreas Vlachos. 2024. Zero-shot fact verification via natural logic and large language models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 17021–17035, Miami, Florida, USA. Association for Computational Linguistics. find
  174. Hao Sun and John Hewitt. 2023. Character-level Chinese backpack language models. In Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, pages 106–119, Singapore. Association for Computational Linguistics. find
  175. Haoran Sun, Renren Jin, Shaoyang Xu, Leiyu Pan, Supryadi, Menglong Cui, Jiangcun Du, Yikun Lei, Lei Yang, Ling Shi, Juesi Xiao, Shaolin Zhu, and Deyi Xiong. 2024. FuxiTranyu: A multilingual large language model trained with balanced data. In Proceedings of the 2024 Conference on Empirical Methods in… find
  176. Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic Attribution for Deep Networks. In Proceedings of the 34th International Conference on Machine Learning, volume 70 of Proceedings of Machine Learning Research, pages 3319–3328, Sydney, Australia. PMLR. ISSN: 2640-3498. find
  177. Kerdkiat Suvirat, Detphop Tanasanchonnakul, Kanakorn Horsiritham, C. Kongkamol, Thammasin Ingviya, and Sitthichok Chaichulee. 2022. Automated Diagnosis Code Assignment of Thai Free-text Clinical Notes. 2022 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE). find
  178. Andrea Tagarelli and Andrea Simeri. 2021. Unsupervised Law Article Mining based on Deep Pre-Trained Language Representation Models with Application to the Italian Civil Code. arXiv preprint. find
  179. Ekaterina Taktasheva, Vladislav Mikhailov, and Ekaterina Artemova. 2021. Shaking syntactic trees on the sesame street: Multilingual probing with controllable perturbations. In Proceedings of the 1st Workshop on Multilingual Representation Learning, pages 191– 210, Punta Cana, Dominican Republic. Ass… find
  180. Tianyi Tang, Wenyang Luo, Haoyang Huang, Dongdong Zhang, Xiaolei Wang, Xin Zhao, Furu Wei, and Ji-Rong Wen. 2024. Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volu…
  181. Shimin Tao, Su Chang, Ma Miaomiao, Hao Yang, Xiang Geng, Shujian Huang, Min Zhang, Jiaxin Guo, Minghan Wang, and Yinglu Li. 2022. find
  182. CrossQE: HW-TSC 2022 submission for the quality estimation shared task. In Proceedings of the Seventh Conference on Machine Translation (WMT), pages 646–652, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics. find
  183. Kushal Tatariya, Heather Lent, Johannes Bjerva, and Miryam de Lhoneux. 2024. Sociolinguistically informed interpretability: A case study on Hinglish emotion classification. In Proceedings of the 6th Workshop on Research in Computational Linguistic Typology and Multilingual NLP, pages 66–74, St. Juli… find
  184. Nguyen Ha Thanh, Vu Tran, Phuong Minh Nguyen, Le-Minh Nguyen, and Ken Satoh. 2023. How Fine Tuning Affects Contextual Embeddings: A Negative Result Explanation. International Conference on Agents and Artificial Intelligence. find
  185. Julia Thomas, Antonia Lucht, Jacob Segler, Richard Wundrack, M. Miché, R. Lieb, Lars Kuchinke, and Gunther Meinlschmidt. 2024. An Explainable Artificial Intelligence Text Classifier for Suicidality Prediction in Youth Crisis Text Line Users: Development and Validation Study. JMIR Public Health and S… find
  186. Baojie Tian, Liangjun Zang, Jizhong Han, and Songlin Hu. 2024. Capture Long-Range Dependency with Meta-Path Transformer for De-Anonymization of Q&A Sites. International Conference on Computer Supported Cooperative Work in Design. find
  187. Isidora Chara Tourni and Derry Tanti Wijaya. 2023. Relevance-guided Neural Machine Translation. arXiv.org. find
  188. Marcos Treviso, Nuno M. Guerreiro, Ricardo Rei, and André F. T. Martins. 2021. find
  189. IST-unbabel 2021 submission for the explainable quality estimation shared task. In Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems, pages 133– 145, Punta Cana, Dominican Republic. Association for Computational Linguistics. find
  190. Dennis Ulmer. 2024. On Uncertainty In Natural Language Processing. arXiv.org. find
  191. Saiteja Utpala, Alex Gu, and Pin-Yu Chen. 2024. Language agnostic code embeddings. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 678–691, Mexico City, Mexico. Associatio… find
  192. Alexandros Vasileiou and Oliver Eberle. 2024. Explaining text similarity in transformer models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 7859–7873, Mexico City, Mex… find
  193. Jesse Vig. 2019. A Multiscale Visualization of Attention in the Transformer Model. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 37– 42, Florence, Italy. Association for Computational Linguistics.
  194. Elena Voita, David Talbot, Fedor Moiseev, Rico Sennrich, and Ivan Titov. 2019. Analyzing multi-head self-attention: Specialized heads do the heavy lifting, the rest can be pruned. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5797–5808, Florence, I…
  195. Davorin Vukadin, A. S. Kurdija, G. Delač, and M. Šilić. 2021. Information Extraction From Free-Form CV Documents in Multiple Languages. IEEE Access. find
  196. Ivan Vulić, Goran Glavaš, Fangyu Liu, Nigel Collier, Edoardo Maria Ponti, and Anna Korhonen. 2023. Probing cross-lingual lexical knowledge from multilingual sentence encoders. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 2089–… find
  197. Ivan Vulić, Edoardo Maria Ponti, Robert Litschko, Goran Glavaš, and Anna Korhonen. 2020. Probing pretrained language models for lexical semantics. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7222–7240, Online. Association for Computationa…
  198. Lennart Wachowiak and Dagmar Gromann. 2022. Systematic analysis of image schemas in natural language through explainable multilingual neural language processing. In Proceedings of the 29th International Conference on Computational Linguistics, pages 5571–5581, Gyeongju, Republic of Korea. Internatio… find
  199. Hetong Wang, Pasquale Minervini, and Edoardo Ponti. 2024a. Probing the emergence of cross-lingual alignment during LLM training. In Findings of the Association for Computational Linguistics: ACL 2024, pages 12159–12173, Bangkok, Thailand. Association for Computational Linguistics. find
  200. Ke Wang, Yangbin Shi, Jiayi Wang, Yuqi Zhang, Yu Zhao, and Xiaolin Zheng. 2021. Beyond glass-box features: Uncertainty quantification enhanced quality estimation for neural machine translation. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4687–4698, Punta Cana, Dom… find
  201. Meiyun Wang, Kiyoshi Izumi, and Hiroki Sakaji. 2024b. LLMFactor: Extracting profitable factors through prompts for explainable stock movement prediction. In Findings of the Association for Computational Linguistics: ACL 2024, pages 3120–3131, Bangkok, Thailand. Association for Computational Linguist… find
  202. Weixuan Wang, B. Haddow, Wei Peng, and Alexandra Birch. 2024c. Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs. arXiv.org. find
  203. Y. Wang, Jonas Pfeiffer, Nicolas Carion, Yann LeCun, and Aishwarya Kamath. 2023. Adapting Grounded Visual Question Answering Models to Low Resource Languages. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). find
  204. Yuqi Wang, Zimu Wang, Nijia Han, Wei Wang, Qi Chen, Haiyang Zhang, Yushan Pan, and Anh Nguyen. 2024d. Knowledge distillation from monolingual to multilingual models for intelligent and interpretable multilingual emotion detection. In Proceedings of the 14th Workshop on Computational Approaches to Su… find
  205. A. Wawer and Justyna Sarzyńska-Wawer. 2022. Detecting Deceptive Utterances Using Deep Pre-Trained Neural Networks. Applied Sciences. find
  206. Sabine Wehnert, Christian Scheel, Simona Szakács-Behling, Maret Nieländer, Patrick Mielke, and Ernesto William De Luca. 2021. HOTTER: Hierarchical optimal topic transport with explanatory context representations. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4856–48… find
  207. Andrea W Wen-Yi and David Mimno. 2023. Hyperpoly-glot LLMs: Cross-lingual interpretability in token embeddings. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 1124–1131, Singapore. Association for Computational Linguistics. find
  208. Chris Wendler, Veniamin Veselovsky, Giovanni Monea, and Robert West. 2024. Do Llamas Work in English? On the Latent Language of Multilingual Transformers. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15366–15394, Bangkok, T…
  209. Tim Z. Xiao, Aidan N. Gomez, and Y. Gal. 2020. Wat zei je? Detecting Out-of-Distribution Translations with Variational Transformers. arXiv.org. find
  210. Chen-Wei Xie, Jianmin Wu, Yun Zheng, Pan Pan, and Xiansheng Hua. 2022. Token Embeddings Alignment for Cross-Modal Retrieval. ACM Multimedia. find
  211. Feng Xiong, Jun Wang, Geng Tu, and Ruifeng Xu. 2024. HITSZ-HLT at WASSA-2024 shared task 2: Language-agnostic multi-task learning for explainability of cross-lingual emotion detection. In Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis… find
  212. Liyan Xu, Xuchao Zhang, Xujiang Zhao, Haifeng Chen, Feng Chen, and Jinho D. Choi. 2021. Boosting cross-lingual transfer via self-learning with uncertainty estimation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6716–6723, Online and Punta Cana, Do… find
  213. Ningyu Xu, Qi Zhang, Jingting Ye, Menghan Zhang, and Xuanjing Huang. 2023. Are structural concepts universal in transformer language models? towards interpretable cross-lingual generalization. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 13951–13976, Singapore. Ass… find
  214. Shanshan Xu and Katja Markert. 2022. The Chinese causative-passive homonymy disambiguation: an adversarial dataset for NLI and a probing task. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 4316–4323, Marseille, France. European Language Resources Association. find
  215. Sihao Xu, Wei Zhang, and Fan Zhang. 2020. Multi-Granular BERT: An Interpretable Model Applicable to Internet-of-Thing devices. 2020 IEEE International Conference on Energy Internet (ICEI). find
  216. Yuemei Xu, Ling Hu, Jiayi Zhao, Zihan Qiu, Kexin XU, Yuqi Ye, and Hanwen Gu. 2024. A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias. ArXiv:2404.00929 [cs]. — [arXiv:2404.00929](https://arxiv.org/abs/2404.00929) find
  217. Yuzi Yan, J. Li, Yipin Zhang, and Dong Yan. 2024. Exploring the LLM Journey from Cognition to Expression with Linear Representations. International Conference on Machine Learning. find
  218. Hao Yang, Min Zhang, Shimin Tao, Minghan Wang, Daimeng Wei, and Yanfei Jiang. 2023a. Knowledge-Prompted Estimator: A Novel Approach to Explainable Machine Translation Assessment. International Conference on Advanced Communication Technology. find
  219. Xianjun Yang, Wei Cheng, Linda Petzold, William Yang Wang, and Haifeng Chen. 2023b. DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text. International Conference on Learning Representations. find
  220. Cuicui Ye, Jing Yang, and Yan Mao. 2024a. FDHFUI: Fusing Deep Representation and Hand-Crafted Features for User Identification. IEEE transactions on consumer electronics. find
  221. Jingheng Ye, Shang Qin, Yinghui Li, Xuxin Cheng, Libo Qin, Hai-Tao Zheng, Peng Xing, Zishan Xu, Guo Cheng, and Zhao Wei. 2024b. EXCGEC: A Benchmark of Edit-wise Explainable Chinese Grammatical Error Correction. arXiv.org. find
  222. Zi yu Chen, Fei Xiao, Xiao kang Wang, Wen hui Hou, Rui Huang, and Jian qiang Wang. 2023. An interpretable diagnostic approach for lung cancer: Combining maximal clique and improved BERT. Expert Syst. J. Knowl. Eng. find
  223. Majid Zarharan, Maryam Hashemi, Malika Behroozrazegh, Sauleh Eetemadi, Mohammad Taher Pilehvar, and Jennifer Foster. 2025. FarExStance: Explainable stance detection for Farsi. In Proceedings of the 31st International Conference on Computational Linguistics, pages 10125–10147, Abu Dhabi, UAE. Associa… find
  224. Hongchuan Zeng, Senyu Han, Lu Chen, and Kai Yu. 2025. Converging to a lingua franca: Evolution of linguistic regions and semantics alignment in multilingual large language models. In Proceedings of the 31st International Conference on Computational Linguistics, pages 10602–10617, Abu Dhabi, UAE. Ass…
  225. Yirong Zeng, Xiao Ding, Yi Zhao, Xiangyu Li, Jie Zhang, Chao Yao, Ting Liu, and Bing Qin. 2024. RU22Fact: Optimizing evidence for multilingual explainable fact-checking on Russia-Ukraine conflict. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resour… find
  226. Wei Zhai, Nan Bai, Qing Zhao, Jianqiang Li, Fan Wang, Hongzhi Qi, Meng Jiang, Xiaoqin Wang, Bing Xiang Yang, and Guanghui Fu. 2024. MentalGLM Series: Explainable Large Language Models for Mental Health Analysis on Chinese Social Media. arXiv.org. find
  227. Ruochen Zhang, Qinan Yu, Matianyu Zang, Carsten Eickhoff, and Ellie Pavlick. 2024a. The Same But Different: Structural Similarities and Differences in Multilingual Language Modeling. arXiv.org. find
  228. Shimao Zhang, Changjiang Gao, Wenhao Zhu, Jiajun Chen, Xin Huang, Xue Han, Junlan Feng, Chao Deng, and Shujian Huang. 2024b. Getting more from less: Large language models are good spontaneous multilingual learners. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Proces… find
  229. Xiaocheng Zhang, Xi Wang, Yifei Lu, Zhuangzhuang Ye, Jianing Wang, Mengjiao Bao, Peng Yan, and Xiaohong Su. 2024c. Augmenting the Veracity and Explanations of Complex Fact Checking via Iterative Self-Revision with LLMs. arXiv.org. find
  230. Ziyin Zhang, Yikang Liu, Weifang Huang, Junyu Mao, Rui Wang, and Hai Hu. 2024d. MELA: Multilingual evaluation of linguistic acceptability. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2658–2674, Bangkok, Thailand. Associati… find
  231. Haiyan Zhao, Hanjie Chen, Fan Yang, Ninghao Liu, Huiqi Deng, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, and Mengnan Du. 2024a. Explainability for Large Language Models: A Survey. ACM Transactions on Intelligent Systems and Technology, 15(2):20:1–20:38.
  232. Shuai Zhao, Qing Li, Yuer Yang, Jinming Wen, and Weiqing Luo. 2023. From Softmax to Nucleusmax: A Novel Sparse Language Model for Chinese Radiology Report Summarization. ACM Trans. Asian Low Resour. Lang. Inf. Process. find
  233. Tiancheng Zhao, Xiaopeng Lu, and Kyusong Lee. 2021. SPARTA: Efficient open-domain question answering via sparse transformer matching retrieval. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 565… find
  234. Xin Zhao, Naoki Yoshinaga, and Daisuke Oba. 2024b. Tracing the roots of facts in multilingual language models: Independent, shared, and transferred knowledge. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages… find
  235. Yiran Zhao, Wenxuan Zhang, Guizhen Chen, Kenji Kawaguchi, and Lidong Bing. 2024c. How do Large Language Models Handle Multilingualism? In Advances in Neural Information Processing Systems 37 (NeurIPS 2024), volume 37, pages 15296–15319, Vancouver, Canada. Curran Associates, Inc.
  236. Zhixue Zhao and Nikolaos Aletras. 2024. Comparing explanation faithfulness between multilingual and monolingual fine-tuned language models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Lon… find
  237. Guorui Zheng, Xidong Wang, Juhao Liang, Nuo Chen, Yuping Zheng, and Benyou Wang. 2024. Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts. arXiv.org. find
  238. Jianyu Zheng and Ying Liu. 2023. What does Chinese BERT learn about syntactic knowledge? PeerJ Computer Science. find
  239. Shaolin Zhu, Supryadi, Shaoyang Xu, Haoran Sun, Leiyu Pan, Menglong Cui, Jiangcun Du, Renren Jin, António Branco, and Deyi Xiong. 2024a. Multilingual Large Language Models: A Systematic Survey. arXiv preprint. ArXiv:2411.11072 [cs]. — [arXiv:2411.11072](https://arxiv.org/abs/2411.11072) find
  240. Wenhao Zhu, Sizhe Liu, Shujian Huang, Shuaijie She, Chris Wendler, and Jiajun Chen. 2024b. Multilingual contrastive decoding via language-agnostic layers skipping. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 8775– 8782, Miami, Florida, USA. Association for Computa… find
  241. Judit Ács, Endre Hamerlik, Roy Schwartz, Noah A. Smith, and András Kornai. 2023. Morphosyntactic probing of multilingual BERT models. Natural Language Engineering.
  242. Judit Ács, D’aniel L’evai, D. Nemeskey, and András Kornai. 2021. Evaluating Contextualized Language Models for Hungarian. arXiv.org. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/resck-2025-explainability-interpretability-multilingual-large-language/