🧑‍🔬 Yonatan Belinkov — all works

49 works · ← Yonatan Belinkov

1. BLOOM: A 176B-Parameter Open-Access Multilingual Language Model ↗arXiv:2211.05100 · no summary yetBigScience Workshop et al.2022 · 1,606 citations
2. Locating and Editing Factual Associations in GPT ↗arXiv:2202.05262 · no summary yetKevin Meng et al.2022 · 1,124 citations
3. Linguistic Knowledge and Transferability of Contextual RepresentationsConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Nelson F. Liu, Matt Gardner, Yonatan Belinkov, et al.2019 · 1,021 citations
4. Analysis Methods in Neural Language Processing: A SurveyTransactions of the Association for Computational Linguistics (TACL)Yonatan Belinkov, James Glass2019 · 740 citations
5. Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction TasksarXiv:1608.04207Yossi Adi, Einat Kermany, Yonatan Belinkov, et al.2016 · 599 citations
6. Probing Classifiers: Promises, Shortcomings, and AdvancesComputational LinguisticsYonatan Belinkov2022 · 529 citations
7. What do Neural Machine Translation Models Learn about Morphology?Annual Meeting of the Association for Computational Linguistics (ACL)Yonatan Belinkov, Nadir Durrani, Fahim Dalvi, et al.2017 · 487 citations
8. Investigating Gender Bias in Language Models Using Causal Mediation Analysis ↗neural information processing systems · no summary yetJesse Vig et al.2020 · 440 citations
9. Analyzing the Structure of Attention in a Transformer Language ModelarXiv:1906.04284Jesse Vig, Yonatan Belinkov2019 · 438 citations
10. Evaluating Layers of Representation in Neural Machine Translation on Part-of-Speech and Semantic Tagging TasksarXiv:1801.07772 · IJCNLP 8 (2017), volume 1, 1-10Yonatan Belinkov, Lluis Marquez, Hassan Sajjad, et al.2017 · 225 citations
11. Jamba: A Hybrid Transformer-Mamba Language ModelarXiv:2403.19887Opher Lieber, Barak Lenz, Hofit Bata, et al.2024 · 159 citations
12. Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance?Conference of the European Chapter of the Association for Computational Linguistics (EACL)Abhilasha Ravichander, Yonatan Belinkov, Eduard Hovy2021 · 144 citations
13. Don't Take the Premise for Granted: Mitigating Artifacts in Natural Language InferenceAnnual Meeting of the Association for Computational Linguistics (ACL)Yonatan Belinkov, Adam Poliak, Stuart Shieber, et al.2019 · 123 citations
14. Identifying and Controlling Important Neurons in Neural Machine Translation ↗arXiv:1811.01157 · no summary yetAnthony Bau et al.2018 · 121 citations
15. A Constructive Prediction of the Generalization Error Across Scales ↗arXiv:1909.12673 · no summary yetJonathan S. Rosenfeld et al.2019 · 120 citations
16. End-to-End Bias Mitigation by Modelling Biases in CorporaAnnual Meeting of the Association for Computational Linguistics (ACL)Rabeeh Karimi Mahabadi, Yonatan Belinkov, James Henderson2020 · 111 citations
17. Analyzing Individual Neurons in Pre-trained Language Models ↗Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · no summary yetNadir Durrani et al.2020 · 111 citations
18. Parallel Context Windows for Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Nir Ratner, Yoav Levine, Yonatan Belinkov, et al.2023 · 102 citations
19. Analyzing Redundancy in Pretrained Transformer Models ↗Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · no summary yetFahim Dalvi et al.2020 · 102 citations
20. On Adversarial Removal of Hypothesis-only Bias in Natural Language InferenceJoint Conference on Lexical and Computational Semantics (*SEM)Yonatan Belinkov, Adam Poliak, Stuart Shieber, et al.2019 · 96 citations
21. Findings of the First Shared Task on Machine Translation Robustness ↗Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1) · no summary yetXian Li et al.2019 · 94 citations
22. Arabic Diacritization with Recurrent Neural NetworksYonatan Belinkov, James GlassSemitic languages · 93 citations
23. LSTM Networks Can Perform Dynamic CountingProceedings of the Workshop on Deep Learning and Formal Languages: Building BridgesMirac Suzgun, Yonatan Belinkov, Stuart Shieber, et al.2019 · 89 citations
24. Similarity Analysis of Contextual Word Representation Models ↗Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · no summary yetJohn Wu et al.2020 · 87 citations
25. Linearity of Relation Decoding in Transformer Language Models ↗arXiv:2308.09124 · no summary yetEvan Hernandez et al.2023 · 82 citations
26. Generating Benchmarks for Factuality Evaluation of Language ModelsConference of the European Chapter of the Association for Computational Linguistics (EACL)Dor Muhlgay, Ori Ram, Inbal Magar, et al.2024 · 81 citations
27. Interpretability and Analysis in Neural NLP ↗Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts · no summary yetYonatan Belinkov, Sebastian Gehrmann, Ellie Pavlick2020 · 73 citations
28. LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations ↗arXiv:2410.02707 · no summary yetHadas Orgad et al.2024 · 68 citations
29. Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms ↗arXiv:2403.17806 · no summary yetMichael Hanna, Sandro Pezzelle, Yonatan Belinkov2024 · 54 citations
30. On the Evaluation of Semantic Phenomena in Neural Machine Translation Using Natural Language Inference ↗Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) · no summary yetAdam Poliak et al.2018 · 52 citations
31. Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics ↗arXiv:2410.21272 · no summary yetYaniv Nikankin et al.2024 · 51 citations
32. Exploring Compositional Architectures and Word Vector Representations for Prepositional Phrase AttachmentYonatan Belinkov, Tao Lei, Regina Barzilay, et al.English · 45 citations
33. Findings of the WMT 2020 Shared Task on Machine Translation Robustness ↗Proceedings of the Fifth Conference on Machine Translation · no summary yetLucia Specia et al.2020 · 39 citations
34. Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech TaggingHassan Sajjad, Fahim Dalvi, Nadir Durrani, et al.Semitic languages · 26 citations
35. Shamela: A Large-Scale Historical Arabic CorpusProceedings of the Workshop on Language Technology Resources and Tools for Digital Humanities (LT4DH)Yonatan Belinkov, Alexander Magidow, Maxim Romanov, et al.2016 · 25 citations
36. A Character-level Convolutional Neural Network for Distinguishing Similar Languages and DialectsWorkshop on NLP for Similar Languages, Varieties and Dialects (VarDial)Yonatan Belinkov, James Glass2016 · 22 citations
37. Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language ModelsConference on Empirical Methods in Natural Language Processing (EMNLP)Zeping Yu, Yonatan Belinkov, Sophia Ananiadou2025 · 16 citations
38. Measuring Chain of Thought Faithfulness by Unlearning Reasoning StepsConference on Empirical Methods in Natural Language Processing (EMNLP)Martin Tutek, Fateme Hashemi Chaleshtori, Ana Marasovic, et al.2025 · 15 citations
39. Large-Scale Machine Translation between Arabic and Hebrew: Available Corpora and Initial ResultsYonatan Belinkov, James GlassModern Hebrew · 14 citations
40. SAEs Are Good for Steering – If You Select the Right FeaturesConference on Empirical Methods in Natural Language Processing (EMNLP)Dana Arad, Aaron Mueller, Yonatan Belinkov2025 · 12 citations
41. Studying the History of the Arabic Language: Language Technology and a Large-Scale Historical CorpusLanguage Resources and EvaluationYonatan Belinkov, Alexander Magidow, Alberto Barron-Cedeno, et al.2018 · 12 citations
42. A Generative Approach for Mitigating Structural Biases in Natural Language InferenceJoint Conference on Lexical and Computational Semantics (*SEM)Dimion Asael, Zachary Ziegler, Yonatan Belinkov2022 · 10 citations
43. Are Formal and Functional Linguistic Mechanisms Dissociated in Language Models?Computational LinguisticsMichael Hanna, Yonatan Belinkov, Sandro Pezzelle2026 · 5 citations
44. Answer Selection in Arabic Community Question Answering: A Feature-Rich ApproachWorkshop on Arabic Natural Language ProcessingYonatan Belinkov, Alberto Barrón-Cedeño, Hamdy Mubarak2015 · 5 citations
45. A Dataset for Metaphor Detection in Early Medieval Hebrew PoetryMichael Toker, Oren Mishali, Ophir Münz-Manor, et al.Ancient Hebrew · 3 citations
46. Mechanisms of Prompt-Induced Hallucination in Vision–Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)William Rudman, Michal Golovanevsky, Dana Arad, et al.2026 · 2 citations
47. Will it Merge? On The Causes of Model MergeabilityFindings of the Association for Computational LinguisticsAdir Rahamim, Asaf Yehudai, Boaz Carmeli, et al.2026
48. Directing large language models to follow the letter or spirit of the law ↗arXiv:2609.23083 · no summary yetPeng Qian et al.2026
49. Part-of-Speech and Morphological Tagging of Algerian Judeo-ArabicNorthern European Journal of Language TechnologyOfra Tirosh-Becker, Michal Kessler, Oren Becker, et al.2022

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/yonatan-belinkov/works/