Elamur Research⌕
☰
home / papers / 2024 / “Seeing the Big through the Small”: Can LLMs Approximate Human Judgment Distributions on NLI from a Few Explanations?

“Seeing the Big through the Small”: Can LLMs Approximate Human Judgment Distributions on NLI from a Few Explanations?

Paper · 2024 · Beiduo Chen, Xinpeng Wang, Siyao Peng et al.

Summary

When several annotators disagree on an NLI item for legitimate reasons, the spread of their labels is informative, and researchers capture it as a human judgment distribution (HJD). Building HJDs usually means paying around a hundred crowd workers per item. Expert datasets are much smaller but come with written explanations. This paper asks whether LLMs can recover a crowd-scale HJD from just a handful of expert explanations.

The authors turn NLI items into multiple-choice prompts. They add the four annotators' explanations from VariErr NLI, either with or without the annotators' labels. They then read a model judgment distribution (MJD) off the first-token probabilities of Mixtral and Llama3, and compare it to the Chaos NLI distributions collected from 100 workers.

Adding explanations clearly moves the MJDs closer to the HJDs. However, MJDs that score similarly on instance-level distances produce noticeably different results when used to fine-tune BERT and RoBERTa. The authors show that distance correlation, a dataset-wide shape measure, combined with visualization, predicts fine-tuning usefulness better. The result is a cheap route to soft labels and a warning about relying on KL-style evaluation alone.

Key points

  • Data sources. Explanations come from VariErr NLI, written by 4 linguists. The target HJDs come from Chaos NLI, with 100 crowd annotations per item. Related resources are Variation NLI (50 workers) and LiveNLI (5 linguists).
  • Prompt variants. There are three: no explanations, explanations given as "comments" without labels, and explanations paired with their explicit labels.
  • How MJDs are obtained. Probabilities come from the first token over the options A/B/C. The order of the answer options and of the explanations is permuted to reduce bias.
  • Why KL alone misleads. A uniform distribution sits at a KL of 0.364 from Chaos NLI, while MNLI one-hot labels sit at 0.665. The uniform baseline still carries nothing useful for training.
  • Mixtral vs. Llama3. Llama3-derived soft labels fine-tuned better. The authors attribute this to their dataset-level shape being closer to Chaos NLI. Code is released as MJD-Estimator.

Interesting ideas

  • I1. Instead of trusting the LLM's single answer, the authors read a distribution from the probabilities of answer letters and average over shuffled option and explanation orders to cancel position bias.
  • I2. A few short human rationales are expanded by an LLM into a full crowd-like distribution, which multiplies the value of scarce expert annotation.
  • I3. Instance-level distances can rank a label set well even when it is useless for training. The uniform baseline beats one-hot labels on KL, so trivial baselines work as a sanity check on the metric itself.
  • I4. Distance correlation compares the pairwise-distance structure of two whole label sets rather than item-by-item gaps, so it captures whether the global shape of variation matches.
  • I5. Giving the label together with its explanation helped the model avoid misreading hedged wording such as "do not mention", which signals Neutral.

For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

  • I1 (learn): LLM teacher tiers could emit graded silver labels this way for ambiguous PP attachments or role choices, giving a calibrated confidence rather than one verdict.
  • I2 (frames): when VerbNet role assignment or an implicature is uncertain, short rationales from witness parsers or annotators could be fed to the teacher to yield a soft distribution over frame readings.
  • I3 (learn): evaluation with negative controls should always score uniform and one-hot baselines alongside silver distributions, so that a metric rewarding emptiness is caught.
  • I4 (learn): it could tell whether a candidate silver corpus reproduces the disagreement structure of a gold treebank before committing GPU time to training gparse on it.
  • I5 (answer): school-test readers could pair each candidate answer with its justification, so negation-like phrasing in rationales is not mistaken for contradiction.

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 Kingdom243 works · 121,396 citations🎓Ludwig-Maximilians-Universität MünchenMunich · Germany107 works · 56,478 citations🎓Munich Center for Machine LearningMunich · Germany57 works · 1,094 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

🧭 Topics 1Research subjects and languages the work is about.Reasoning · 1,426 works

Cite

Cite as Beiduo Chen, Xinpeng Wang, Siyao Peng, Robert Litschko, Anna Korhonen and Barbara Plank. 2024. “Seeing the Big through the Small”: Can LLMs Approximate Human Judgment Distributions on NLI from a Few Explanations?. Findings of the Association for Computational Linguistics: EMNLP 2024.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2024.findings-emnlp.842

@inproceedings{chen2024seeing,
  title = {{“Seeing the Big through the Small”: Can LLMs Approximate Human Judgment Distributions on NLI from a Few Explanations?}},
  author = {Beiduo Chen, Xinpeng Wang, Siyao Peng, Robert Litschko, Anna Korhonen and Barbara Plank},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2024},
  year = {2024},
  doi = {10.18653/v1/2024.findings-emnlp.842},
  url = {https://doi.org/10.18653/v1/2024.findings-emnlp.842}
}

References

56 references, 31 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Sanchit Ahuja, Divyanshu Aggarwal, Varun Gumma, Ishaan Watts, Ashutosh Sathe, Millicent Ochieng, Rishav Hada, Prachi Jain, Maxamed Axmed, Kalika Bali, and Sunayana Sitaram. 2024. MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks. Preprint, arXiv:2311.07463. ↗
  2. Abhishek Anand, Negar Mokhberian, Prathyusha Kumar, Anweasha Saha, Zihao He, Ashwin Rao, Fred Morstatter, and Kristina Lerman. 2024. Don’t blame the data, blame the model: Understanding noise and bias when learning from subjective annotations. In Proceedings of the 1st Workshop on Uncertainty-Aware NLP (UncertaiNLP 2024), pages 102–113, St Julians, Malta. Association for Computational Linguistics. ↗
  3. Lora Aroyo and Chris Welty. 2015. Truth is a lie: Crowd truth and the seven myths of human annotation. AI Mag., 36(1):15–24. ↗
  4. Joris Baan, Wilker Aziz, Barbara Plank, and Raquel Fernandez. 2022. Stop measuring calibration when humans disagree. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 1892–1915, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics. find
  5. Simone Balloccu, Patrícia Schmidtová, Mateusz Lango, and Ondrej Dusek. 2024. Leak, cheat, repeat: Data contamination and evaluation malpractices in closed-source LLMs. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 67–93, St. Julian’s, Malta. Association for Computational Linguistics. ↗
  6. Parishad BehnamGhader, Vaibhav Adlakha, Marius Mosbach, Dzmitry Bahdanau, Nicolas Chapados, and Siva Reddy. 2024. LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders. Preprint, arXiv:2404.05961. ↗
  7. Samuel R. Bowman, Gabor Angeli, Christopher Potts, and Christopher D. Manning. 2015. A large annotated corpus for learning natural language inference. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015, Lisbon, Portugal, September 17-21, 2015, pages 632–642. The Association for Computational Linguistics. ↗
  8. Federico Cabitza, Andrea Campagner, and Valerio Basile. 2023. Toward a perspectivist turn in ground truthing for predictive computing. In Proceedings of the AAAI Conference on Artificial Intelligence.
  9. Cheng-Han Chiang and Hung-yi Lee. 2023. Can large language models be an alternative to human evaluations? In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15607–15631, Toronto, Canada. Association for Computational Linguistics. find
  10. Alexis Conneau, Ruty Rinott, Guillaume Lample, Adina Williams, Samuel Bowman, Holger Schwenk, and Veselin Stoyanov. 2018. XNLI: Evaluating cross-lingual sentence representations. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2475–2485, Brussels, Belgium. Association for Computational Linguistics. ↗
  11. Ido Dagan, Oren Glickman, and Bernardo Magnini. 2005. The PASCAL recognising textual entailment challenge. In Machine Learning Challenges, Evaluating Predictive Uncertainty, Visual Object Classification and Recognizing Textual Entailment, First PASCAL Machine Learning Challenges Workshop, MLCW 2005, Southampton, UK, April 11-13, 2005, Revised Selected Papers, volume 3944 of Lecture Notes in Computer Science, pages 177–190. Springer. find
  12. Aida Mostafazadeh Davani, Mark Díaz, and Vinodkumar Prabhakaran. 2022. Dealing with disagreements: Looking beyond the majority vote in subjective annotations. Trans. Assoc. Comput. Linguistics, 10:92– 110. ↗
  13. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers), pages 4171–4186. Association for Computational Linguistics.
  14. Luc Devroye and Gábor Lugosi. 2001. Combinatorial methods in density estimation. Springer series in statistics. Springer. ↗
  15. Ricardo Dominguez-Olmedo, Moritz Hardt, and Celestine Mendler-Dünner. 2023. Questioning the Survey Responses of Large Language Models. CoRR, abs/2306.07951. ↗
  16. Dominik Maria Endres and Johannes E. Schindelin. 2003. A new metric for probability distributions. IEEE Trans. Inf. Theory, 49(7):1858–1860. ↗
  17. Allyson Ettinger, Jena Hwang, Valentina Pyatkin, Chandra Bhagavatula, and Yejin Choi. 2023. “you are an expert linguistic annotator”: Limits of LLMs as analyzers of Abstract Meaning Representation. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 8250–8263, Singapore. Association for Computational Linguistics. find
  18. Tommaso Fornaciari, Alexandra Uma, Silviu Paun, Barbara Plank, Dirk Hovy, and Massimo Poesio. 2021a. Beyond black & white: Leveraging annotator disagreement via soft-label multi-task learning. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2021, Online, June 6-11, 2021, pages 2591– 2597. Association for Computational Linguistics.
  19. Tommaso Fornaciari, Alexandra Uma, Silviu Paun, Barbara Plank, Dirk Hovy, and Massimo Poesio. 2021b. Beyond black & white: Leveraging annotator disagreement via soft-label multi-task learning. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2591–2597, Online. Association for Computational Linguistics.
  20. Cornelia Gruber, Katharina Hechinger, Matthias Assenmacher, Göran Kauermann, and Barbara Plank. 2024. More labels or cases? assessing label variation in natural language inference. In Proceedings of the Third Workshop on Understanding Implicit and Underspecified Language, pages 22–32, Malta. Association for Computational Linguistics.
  21. Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, Lélio Renard Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, and William El Sayed. 2023a. Mistral 7B. Preprint, arXiv:2310.06825. ↗
  22. Albert Q. Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de Las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Sandeep Subramanian, Sophia Yang, Szymon Antoniak, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, and William El Sayed. 2024. Mixtral of Experts. CoRR, abs/2401.04088. ↗
  23. Nan-Jiang Jiang and Marie-Catherine de Marneffe. 2022a. Investigating reasons for disagreement in natural language inference. Transactions of the Association for Computational Linguistics, 10:1357– 1374. ↗
  24. Nan-Jiang Jiang, Chenhao Tan, and Marie-Catherine de Marneffe. 2023b. Ecologically valid explanations for label variation in NLI. In Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023, pages 10622– 10633. Association for Computational Linguistics.
  25. Nanjiang Jiang and Marie-Catherine de Marneffe. 2022b. Investigating reasons for disagreement in natural language inference. Trans. Assoc. Comput. Linguistics, 10:1357–1374. ↗
  26. Solomon Kullback and Richard A Leibler. 1951. On information and sufficiency. The annals of mathematical statistics, 22(1):79–86. ↗
  27. Andrew K. Lampinen, Ishita Dasgupta, Stephanie C. Y. Chan, Kory W. Mathewson, Michael Henry Tessler, Antonia Creswell, James L. McClelland, Jane Wang, and Felix Hill. 2022. Can language models learn from explanations in context? In Findings of the Association for Computational Linguistics: EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022, pages 537–563. Association for Computational Linguistics. ↗
  28. Dong-Ho Lee, Jay Pujara, Mohit Sewak, Ryen White, and Sujay Kumar Jauhar. 2023a. Making large language models better data creators. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023, pages 15349–15360. Association for Computational Linguistics. find
  29. Noah Lee, Na An, and James Thorne. 2023b. Can large language models capture dissenting human voices? In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023, pages 4569– 4585. Association for Computational Linguistics. find
  30. Elisa Leonardelli, Gavin Abercrombie, Dina Almanea, Valerio Basile, Tommaso Fornaciari, Barbara Plank, Verena Rieser, Alexandra Uma, and Massimo Poesio. 2023. SemEval-2023 task 11: Learning with disagreements (LeWiDi). In Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023), pages 2304–2318, Toronto, Canada. Association for Computational Linguistics. ↗
  31. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR, abs/1907.11692. ↗
  32. Christopher D. Manning. 2006. Local textual inference : It’s hard to circumscribe , but you know it when you see it - and nlp needs it. find
  33. Meta. 2024. Introducing Meta Llama 3: The most capable openly available LLM to date. https://ai.meta.com/blog/meta-llama-3/. ↗
  34. Rafael Müller, Simon Kornblith, and Geoffrey E. Hinton. 2019. When does label smoothing help? In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, pages 4696–4705. find
  35. Yixin Nie, Xiang Zhou, and Mohit Bansal. 2020. What can we learn from collective human opinions on natural language inference data? In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, November 16-20, 2020, pages 9131–9143. Association for Computational Linguistics.
  36. Yonatan Oren, Nicole Meister, Niladri S. Chatterji, Faisal Ladhak, and Tatsunori Hashimoto. 2024. Proving test set contamination in black-box language models. In The Twelfth International Conference on Learning Representations. ↗
  37. Ellie Pavlick and Tom Kwiatkowski. 2019. Inherent disagreements in human textual inferences. Trans. Assoc. Comput. Linguistics, 7:677–694. ↗
  38. Maja Pavlovic and Massimo Poesio. 2024. The effectiveness of LLMs as annotators: A comparative overview and empirical analysis of direct representation. In Proceedings of the 3rd Workshop on Perspectivist Approaches to NLP (NLPerspectives) @ LREC-COLING 2024, pages 100–110, Torino, Italia. ELRA and ICCL.
  39. Barbara Plank. 2022. The "problem" of human label variation: On ground truth in data, modeling and evaluation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022, pages 10671–10682. Association for Computational Linguistics. ↗
  40. Barbara Plank, Dirk Hovy, and Anders Søgaard. 2014. Learning part-of-speech taggers with inter-annotator agreement loss. In Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, pages 742–751, Gothenburg, Sweden. Association for Computational Linguistics. ↗
  41. Marta Sandri, Elisa Leonardelli, Sara Tonelli, and Elisabetta Jezek. 2023. Why don’t you do it right? analysing annotators’ disagreement in subjective tasks. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023, Dubrovnik, Croatia, May 2-6, 2023, pages 2420–2433. Association for Computational Linguistics. find
  42. Gábor J. Székely, Maria L. Rizzo, and Nail K. Bakirov. 2007. Measuring and testing dependence by correlation of distances. The Annals of Statistics, 35(6):2769–2794. ↗
  43. Lindia Tjuatja, Valerie Chen, Sherry Tongshuang Wu, Ameet Talwalkar, and Graham Neubig. 2023. Do LLMs exhibit human-like response biases? A case study in survey design. CoRR, abs/2311.04076. ↗
  44. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fuller, Cynthia Gao, Vedanuj Goswami, Naman Goyal, Anthony Hartshorn, Saghar Hosseini, Rui Hou, Hakan Inan, Marcin Kardas, Viktor Kerkez, Madian Khabsa, Isabel Kloumann, Artem Korenev, Punit Singh Koura, Marie-Anne Lachaux, Thibaut Lavril, Jenya Lee, Diana Liskovich, Yinghai Lu, Yuning Mao, Xavier Martinet, Todor Mihaylov, Pushkar Mishra, Igor Molybog, Yixin Nie, Andrew Poulton, Jeremy Reizenstein, Rashi Rungta, Kalyan Saladi, Alan Schelten, Ruan Silva, Eric Michael Smith, Ranjan Subramanian, Xiaoqing Ellen Tan, Binh Tang, Ross Taylor, Adina Williams, Jian Xiang Kuan, Puxin Xu, Zheng Yan, Iliyan Zarov, Yuchen Zhang, Angela Fan, Melanie Kambadur, Sharan Narang, Aurelien Rodriguez, Robert Stojnic, Sergey Edunov, and Thomas Scialom. 2023. Llama 2: Open foundation and fine-tuned chat models. Preprint, arXiv:2307.09288. ↗
  45. Alexandra Uma, Tommaso Fornaciari, Dirk Hovy, Silviu Paun, Barbara Plank, and Massimo Poesio. 2021. Learning from disagreement: A survey. J. Artif. Intell. Res., 72:1385–1470. ↗
  46. Pat Verga, Sebastian Hofstatter, Sophia Althammer, Yixuan Su, Aleksandra Piktus, Arkady Arkhangorodsky, Minjie Xu, Naomi White, and Patrick Lewis. 2024. Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models. Preprint, arXiv:2404.18796. ↗
  47. Manya Wadhwa, Jifan Chen, Junyi Jessy Li, and Greg Durrett. 2023. Using Natural Language Explanations to Rescale Human Judgments. CoRR, abs/2305.14770. ↗
  48. Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R. Bowman. 2019. GLUE: A multi-task benchmark and analysis platform for natural language understanding. In International Conference on Learning Representations. ↗
  49. Leon Weber-Genzel, Siyao Peng, Marie-Catherine de Marneffe, and Barbara Plank. 2024. VariErr NLI: Separating Annotation Error from Human Label Variation. CoRR, abs/2403.01931. ↗
  50. Hongxin Wei, Renchunzi Xie, Hao Cheng, Lei Feng, Bo An, and Yixuan Li. 2022a. Mitigating neural network overconfidence with logit normalization. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA, volume 162 of Proceedings of Machine Learning Research, pages 23631–23644. PMLR. ↗
  51. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 2022b. Chain-of-thought prompting elicits reasoning in large language models. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022.
  52. Adina Williams, Nikita Nangia, and Samuel R. Bowman. 2018. A broad-coverage challenge corpus for sentence understanding through inference. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2018, New Orleans, Louisiana, USA, June 1-6, 2018, Volume 1 (Long Papers), pages 1112–1122. Association for Computational Linguistics. ↗
  53. Xiaohan Xu, Ming Li, Chongyang Tao, Tao Shen, Reynold Cheng, Jinyang Li, Can Xu, Dacheng Tao, and Tianyi Zhou. 2024. A Survey on Knowledge Distillation of Large Language Models. CoRR, abs/2402.13116. ↗
  54. Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, Yifan Du, Chen Yang, Yushuo Chen, Zhipeng Chen, Jinhao Jiang, Ruiyang Ren, Yifan Li, Xinyu Tang, Zikang Liu, Peiyu Liu, Jian-Yun Nie, and Ji-Rong Wen. 2023. A Survey of Large Language Models. CoRR, abs/2303.18223. ↗
  55. Chujie Zheng, Hao Zhou, Fandong Meng, Jie Zhou, and Minlie Huang. 2024. Large language models are not robust multiple choice selectors. In The Twelfth International Conference on Learning Representations. ↗
  56. Xiang Zhou, Yixin Nie, and Mohit Bansal. 2022. Distributed NLI: Learning to predict human opinion distributions for language reasoning. In Findings of the Association for Computational Linguistics: ACL 2022, pages 972–987, Dublin, Ireland. Association for Computational Linguistics.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/chen-2024-seeing-big-through-small-can/