Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

We're Afraid Language Models Aren't Modeling Ambiguity (2304.14399v2)

Published 27 Apr 2023 in cs.CL

Abstract: Ambiguity is an intrinsic feature of natural language. Managing ambiguity is a key part of human language understanding, allowing us to anticipate misunderstanding as communicators and revise our interpretations as listeners. As LLMs (LMs) are increasingly employed as dialogue interfaces and writing aids, handling ambiguous language is critical to their success. We characterize ambiguity in a sentence by its effect on entailment relations with another sentence, and collect AmbiEnt, a linguist-annotated benchmark of 1,645 examples with diverse kinds of ambiguity. We design a suite of tests based on AmbiEnt, presenting the first evaluation of pretrained LMs to recognize ambiguity and disentangle possible meanings. We find that the task remains extremely challenging, including for GPT-4, whose generated disambiguations are considered correct only 32% of the time in human evaluation, compared to 90% for disambiguations in our dataset. Finally, to illustrate the value of ambiguity-sensitive tools, we show that a multilabel NLI model can flag political claims in the wild that are misleading due to ambiguity. We encourage the field to rediscover the importance of ambiguity for NLP.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (51)
  1. Testing pre-trained language models’ understanding of distributivity via causal mediation analysis. In Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, pages 314–324, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
  2. Beata Beigman Klebanov and Eyal Beigman. 2009. From annotator agreement to noise models. Computational Linguistics, 35(4):495–503.
  3. A large annotated corpus for learning natural language inference. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 632–642, Lisbon, Portugal. Association for Computational Linguistics.
  4. Andrew Carnie. 2013. Syntax: A Generative Introduction. Introducing Linguistics. Wiley.
  5. Generating literal and implied subquestions to fact-check complex claims. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3495–3516, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
  6. Uncertain natural language inference. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8772–8779, Online. Association for Computational Linguistics.
  7. Scaling instruction-finetuned language models.
  8. Kenneth Church and Ramesh Patil. 1982. Coping with syntactic ambiguity or how to put the block in the box on the table. American Journal of Computational Linguistics, 8(3-4):139–149.
  9. Selectively answering ambiguous questions.
  10. Ann Copestake and Dan Flickinger. 2000. An open source grammar development environment and broad-coverage English grammar using HPSG. In Proceedings of the Second International Conference on Language Resources and Evaluation (LREC’00), Athens, Greece. European Language Resources Association (ELRA).
  11. RealToxicityPrompts: Evaluating neural toxic degeneration in language models. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3356–3369, Online. Association for Computational Linguistics.
  12. Jury learning: Integrating dissenting voices into machine learning models. In Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems, CHI ’22, New York, NY, USA. Association for Computing Machinery.
  13. Barbara J. Grosz. 1977. The Representation and Use of Focus in Dialogue Understanding. Ph.D. thesis.
  14. The curious case of neural text degeneration. In International Conference on Learning Representations.
  15. Are natural language inference models IMPPRESsive? Learning IMPlicature and PRESupposition. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8690–8705, Online. Association for Computational Linguistics.
  16. Nan-Jiang Jiang and Marie-Catherine de Marneffe. 2022. Investigating Reasons for Disagreement in Natural Language Inference. Transactions of the Association for Computational Linguistics, 10:1357–1374.
  17. Kate Kearns. 2000. Semantics. St. Martin’s Press.
  18. Regular tree grammars as a formalism for scope underspecification. In Proceedings of ACL-08: HLT, pages 218–226, Columbus, Ohio. Association for Computational Linguistics.
  19. Assistance with large language models. In Proceedings of the ML Safety Workshop at NeurIPS.
  20. Clam: Selective clarification for ambiguous questions with generative language models. In Proceedings of the Workshop on Challenges in Deployable Generative AI at International Conference on Machine Learning (ICML).
  21. Coauthor: Designing a human-AI collaborative writing dataset for exploring language model capabilities. In CHI Conference on Human Factors in Computing Systems, New Orleans, LA, USA.
  22. WANLI: Worker and AI collaboration for natural language inference dataset creation. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 6826–6847, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
  23. Embracing ambiguity: Shifting the training target of NLI models. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 862–869, Online. Association for Computational Linguistics.
  24. Meta. 2022. No language left behind: Scaling human-centered machine translation.
  25. AmbigQA: Answering ambiguous open-domain questions. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 5783–5797, Online. Association for Computational Linguistics.
  26. 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), pages 9131–9143, Online. Association for Computational Linguistics.
  27. OpenAI. 2022. Introducing ChatGPT.
  28. OpenAI. 2023. GPT-4 technical report.
  29. Training language models to follow instructions with human feedback.
  30. Ellie Pavlick and Tom Kwiatkowski. 2019. Inherent disagreements in human textual inferences. Transactions of the Association for Computational Linguistics, 7:677–694.
  31. Sandro Pezzelle. 2023. Dealing with semantic underspecification in multimodal NLP. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12098–12112, Toronto, Canada. Association for Computational Linguistics.
  32. The communicative function of ambiguity in language. Cognition, 122(3):280–291.
  33. 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, pages 10671–10682, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
  34. Massimo Poesio and Ron Artstein. 2005. The reliability of anaphoric annotation, reconsidered: Taking ambiguity into account. In Proceedings of the Workshop on Frontiers in Corpus Annotations II: Pie in the Sky, pages 76–83, Ann Arbor, Michigan. Association for Computational Linguistics.
  35. Annotators with attitudes: How annotator beliefs and identities bias toxic language detection. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5884–5906, Seattle, United States. Association for Computational Linguistics.
  36. The woman worked as a babysitter: On biases in language generation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3407–3412, Hong Kong, China. Association for Computational Linguistics.
  37. Blenderbot 3: a deployed conversational agent that continually learns to responsibly engage.
  38. Conceptnet 5.5: An open multilingual graph of general knowledge. In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, page 4444–4451. AAAI Press.
  39. Why did the chicken cross the road? Rephrasing and analyzing ambiguous questions in VQA. In Proceedings of the 61th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics.
  40. Task ambiguity in humans and language models. In The Eleventh International Conference on Learning Representations.
  41. Lewis Thomas. 1974. The lives of a cell. Notes of a biology watcher, New york (The Viking Press) 1974.
  42. LLaMA: Open and efficient foundation language models.
  43. SemEval-2021 task 12: Learning with disagreements. In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 338–347, Online. Association for Computational Linguistics.
  44. GLUE: A multi-task benchmark and analysis platform for natural language understanding. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 353–355, Brussels, Belgium. Association for Computational Linguistics.
  45. 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, Volume 1 (Long Papers), pages 1112–1122, New Orleans, Louisiana. Association for Computational Linguistics.
  46. AmbiCoref: Evaluating human and model sensitivity to ambiguous coreference. In Findings of the Association for Computational Linguistics: EACL 2023, pages 1023–1030, Dubrovnik, Croatia. Association for Computational Linguistics.
  47. Ordinal common-sense inference. Transactions of the Association for Computational Linguistics, 5:379–395.
  48. Learning with different amounts of annotation: From zero to many labels. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7620–7632, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
  49. Xinliang Frederick Zhang and Marie-Catherine de Marneffe. 2021. Identifying inherent disagreement in natural language inference. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4908–4915, Online. Association for Computational Linguistics.
  50. 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.
  51. George Kingsley Zipf. 1949. Human behavior and the principle of least effort.
Citations (70)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now