Elamur Research⌕
☰
home / papers / 2026 / Arguments that Alter Minds: LLM Rationales Sway Human (and LLM) Notions of Plausibility

Arguments that Alter Minds: LLM Rationales Sway Human (and LLM) Notions of Plausibility

Paper · 2026 · Shramay Palta, Peter A. Rankel, Sarah Wiegreffe et al.

Summary

Multiple-choice commonsense benchmarks assume that the gold answer is the one people find most plausible. But most answers are neither certain nor impossible, so arguments can push their plausibility up or down. This paper asks whether LLM-written arguments change how humans, and LLMs, rate an answer's plausibility.

The authors sampled 100 questions from Social IQA (SIQA) and CommonsenseQA (CQA), each paired with its gold answer and one random distractor. GPT-4o, chosen in a small human preference study, wrote a PRO and a CON rationale for every pair. Humans on Prolific and 17 LLMs then rated each answer on a 5-point Likert scale. Ratings were collected with a PRO rationale, a CON rationale, or both. These were compared with earlier no-rationale ratings from Palta et al. (2024).

PRO rationales generally raised ratings and CON rationales lowered them, for both humans and models. One exception: humans gave gold answers lower ratings when shown a PRO argument. Answers that started out more plausible shifted less. The findings suggest LLMs can sway everyday intuitions, which raises concerns about persuasion and manipulation.

Key points

  • Dataset scale: 3,000 new human judgments and 13,600 LLM judgments over 200 (q, a) pairs. The released data (AAM repository on GitHub) also reuses 1,000 earlier no-rationale ratings.
  • Choosing the rationale model: GPT-4o was compared against GPT-4o-mini, Llama 3.1-8B-Instruct and Llama 3.1-70B-Instruct. Four annotators judged rationales for 40 SIQA validation pairs, and GPT-4o received the most votes.
  • Effect of CON rationales: they lowered mean human ratings in 69% of SIQA pairs and 33% of CQA pairs. For OpenAI models the figure reached 84% on SIQA, a stronger reaction than humans showed.
  • Mixed and anchoring effects: showing PRO and CON together lowered ratings for gold answers but raised them for distractors. An OLS regression confirmed anchoring for every rater group, and the effect was stronger for distractors.
  • Limitations: the study covers only English-language data and US-based annotators, and only GPT-4o generated the rationales.

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 Maryland, College ParkCollege Park · United States132 works · 25,380 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.Language models & pretraining · 3,320 works

Cite

Cite as Shramay Palta, Peter A. Rankel, Sarah Wiegreffe and Rachel Rudinger. 2026. Arguments that Alter Minds: LLM Rationales Sway Human (and LLM) Notions of Plausibility. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.599

@inproceedings{palta2026arguments,
  title = {{Arguments that Alter Minds: LLM Rationales Sway Human (and LLM) Notions of Plausibility}},
  author = {Shramay Palta, Peter A. Rankel, Sarah Wiegreffe and Rachel Rudinger},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.599},
  url = {https://doi.org/10.18653/v1/2026.acl-long.599}
}

References

65 references, 18 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Christabel Acquaye, Haozhe An, and Rachel Rudinger. 2024. Susu box or piggy bank: Assessing cultural commonsense knowledge between Ghana and the US. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 9483–9502, Miami, Florida, USA. Association for Comput…
  2. Vicky Arnold, Philip A Collier, Stewart A Leech, and Steve G Sutton. 2000. The effect of experience and complexity on order and recency bias in decision making by professional accountants. Accounting & Finance, 40(2):109–134. find
  3. Gagan Bansal, Tongshuang Wu, Joyce Zhou, Raymond Fok, Besmira Nushi, Ece Kamar, Marco Tulio Ribeiro, and Daniel Weld. 2021. Does the whole exceed its parts? the effect of ai explanations on complementary team performance. In Proceedings of the 2021 CHI Conference on Human Factors in Computing System… find
  4. Rafael M. Batista and Thomas L. Griffiths. 2026. A rational analysis of the effects of sycophantic ai. Preprint, arXiv:2602.14270. — [arXiv:2602.14270](https://arxiv.org/abs/2602.14270) find
  5. Chandra Bhagavatula, Ronan Le Bras, Chaitanya Malaviya, Keisuke Sakaguchi, Ari Holtzman, Hannah Rashkin, Doug Downey, Wen tau Yih, and Yejin Choi. 2020. Abductive commonsense reasoning. In International Conference on Learning Representations.
  6. Mehar Bhatia and Vered Shwartz. 2023. GD-COMET: A geo-diverse commonsense inference model. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 7993–8001, Singapore. Association for Computational Linguistics. find
  7. Or Biran and Kathleen McKeown. 2017. Human-centric justification of machine learning predictions. In Proceedings of the 26th International Joint Conference on Artificial Intelligence, IJCAI’17, page 1461–1467. AAAI Press. find
  8. Faeze Brahman, Vered Shwartz, Rachel Rudinger, and Yejin Choi. 2021. Learning to rationalize for non-monotonic reasoning with distant supervision. Proceedings of the AAAI Conference on Artificial Intelligence, 35(14):12592–12601. find
  9. Oana-Maria Camburu, Tim Rocktäschel, Thomas Lukasiewicz, and Phil Blunsom. 2018. e-snli: Natural language inference with natural language explanations. In Advances in Neural Information Processing Systems, volume 31. Curran Associates, Inc.
  10. Chacha Chen, Shi Feng, Amit Sharma, and Chenhao Tan. 2023. Machine explanations and human understanding. In Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency, FAccT ’23, page 1, New York, NY, USA. Association for Computing Machinery. find
  11. Tongfei Chen, Zhengping Jiang, Adam Poliak, Keisuke Sakaguchi, and Benjamin Van Durme. 2020. 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.
  12. DeepSeek-AI. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. Preprint, arXiv:2501.12948.
  13. James N. Druckman. 2001. Evaluating framing effects. Journal of Economic Psychology, 22(1):91–101. find
  14. Laurette Dube-Rioux and J. Edward Russo. 1988. An availability bias in professional judgment. Journal of Behavioral Decision Making, 1(4):223–237. find
  15. Shi Feng and Jordan Boyd-Graber. 2019. What can ai do for me? evaluating machine learning interpretations in cooperative play. In Proceedings of the 24th International Conference on Intelligent User Interfaces, IUI ’19, page 229–239, New York, NY, USA. Association for Computing Machinery. find
  16. Raymond Fok and Daniel S Weld. 2024. In search of verifiability:: Explanations rarely enable complementary performance in ai-advised decision making. AI Magazine, 45(3):317–332. find
  17. Valerie S. Folkes. 1988. The availability heuristic and perceived risk. Journal of Consumer Research, 15(1):13–23. find
  18. Ana Valeria González, Gagan Bansal, Angela Fan, Yashar Mehdad, Robin Jia, and Srinivasan Iyer. 2021. Do explanations help users detect errors in open-domain QA? an evaluation of spoken vs. visual explanations. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 1103–… find
  19. Navita Goyal, Eleftheria Briakou, Amanda Liu, Connor Baumler, Claire Bonial, Jeffrey Micher, Clare Voss, Marine Carpuat, and Hal Daumé III. 2023. What else do I need to know? the effect of background information on users’ reliance on QA systems. In Proceedings of the 2023 Conference on Empirical Met… find
  20. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, and 1 others. 2024. The llama 3 herd of models. Preprint, arXiv:2407.21783.
  21. Herbert P Grice. 1975. Logic and conversation. In Speech acts, pages 41–58. Brill. find
  22. Lisa Anne Hendricks, Zeynep Akata, Marcus Rohrbach, Jeff Donahue, Bernt Schiele, and Trevor Darrell. 2016. Generating visual explanations. In Proceedings of the 14th European Conference on Computer Vision (ECCV), Amsterdam, Netherlands. find
  23. Daniel Hershcovich, Stella Frank, Heather Lent, Miryam de Lhoneux, Mostafa Abdou, Stephanie Brandl, Emanuele Bugliarello, Laura Cabello Piqueras, Ilias Chalkidis, Ruixiang Cui, Constanza Fierro, Katerina Margatina, Phillip Rust, and Anders Søgaard. 2022. Challenges and strategies in cross-cultural N…
  24. Alon Jacovi, Ana Marasović, Tim Miller, and Yoav Goldberg. 2021. Formalizing trust in artificial intelligence: Prerequisites, causes and goals of human trust in ai. In Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, FAccT ’21, page 624–635, New York, NY, USA. A… find
  25. 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, and 1 others. 2024. Mixtral of experts. Preprint, arXiv:2401.04088. find
  26. Edward E Jones and Steven Bergias. 1976. A recency effect in attitude attribution. Journal of Personality, 44(3). find
  27. Brihi Joshi, Ziyi Liu, Sahana Ramnath, Aaron Chan, Zhewei Tong, Shaoliang Nie, Qifan Wang, Yejin Choi, and Xiang Ren. 2023. Are machine rationales (not) useful to humans? measuring and improving human utility of free-text rationales. In Proceedings of the 61st Annual Meeting of the Association for C… find
  28. Arie W Kruglanski and Icek Ajzen. 1983. Bias and error in human judgment. European Journal of Social Psychology, 13(1):1–44. find
  29. Mary Kynn. 2007. The ‘heuristics and biases’ bias in expert elicitation. Journal of the Royal Statistical Society Series A: Statistics in Society, 171(1):239– 264. find
  30. Andrew Lampinen, Ishita Dasgupta, Stephanie Chan, Kory Mathewson, Mh Tessler, Antonia Creswell, James 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, pages 537–563, Abu Dhab…
  31. Veronica Latcinnik and Jonathan Berant. 2020. Explaining question answering models through text generation. arXiv preprint arXiv:2004.05569. — [arXiv:2004.05569](https://arxiv.org/abs/2004.05569) find
  32. Mina Lee, Megha Srivastava, Amelia Hardy, John Thickstun, Esin Durmus, Ashwin Paranjape, Ines Gerard-Ursin, Xiang Lisa Li, Faisal Ladhak, Frieda Rong, Rose E Wang, Minae Kwon, Joon Sung Park, Hancheng Cao, Tony Lee, Rishi Bommasani, Michael S. Bernstein, and Percy Liang. 2023. Evaluating human-langu… find
  33. Hector J. Levesque, Ernest Davis, and L. Morgenstern. 2011. The winograd schema challenge. In AAAI Spring Symposium: Logical Formalizations of Commonsense Reasoning. find
  34. Jiacheng Liu, Wenya Wang, Dianzhuo Wang, Noah Smith, Yejin Choi, and Hannaneh Hajishirzi. 2023. Vera: A general-purpose plausibility estimation model for commonsense statements. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 1264–1287, Singapore. Ass… find
  35. David R Mandel. 2014. Do framing effects reveal irrational choice? Journal of Experimental Psychology: General, 143(3):1185. find
  36. Ana Marasovic, Iz Beltagy, Doug Downey, and Matthew Peters. 2022. Few-shot self-rationalization with natural language prompts. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 410–424, Seattle, United States. Association for Computational Linguistics.
  37. André C. R. Martins. 2006. Probability biases as bayesian inference. Judgment and Decision Making, 1(2):108–117. find
  38. Nasrin Mostafazadeh, Nathanael Chambers, Xiaodong He, Devi Parikh, Dhruv Batra, Lucy Vanderwende, Pushmeet Kohli, and James Allen. 2016. A corpus and cloze evaluation for deeper understanding of commonsense stories. In Proceedings of the 2016 Conference of the North American Chapter of the Associati… find
  39. Nadia Hanin Nazlan, Sarah Tanford, and Rhonda Montgomery. 2018. The effect of availability heuristics in online consumer reviews. Journal of Consumer Behaviour, 17(5):449–460. find
  40. OpenAI, :, Aaron Hurst, Adam Lerer, Adam P. Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, Aleksander M adry, Alex Baker-Whitcomb, Alex Beutel, and 1 others. 2024a. Gpt-4o system card. Preprint, arXiv:2410.21276.
  41. OpenAI, :, Aaron Jaech, Adam Kalai, Adam Lerer, Adam Richardson, Ahmed El-Kishky, Aiden Low, Alec Helyar, Aleksander Madry, Alex Beutel, Alex Carney, Alex Iftimie, Alex Karpenko, Alex Tachard Passos, and 1 others. 2024b. Openai o1 system card. Preprint, arXiv:2412.16720.
  42. OpenAI, Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, and 1 others. 2024c. Gpt-4 technical report. Preprint, arXiv:2303.08774.
  43. Thorsten Pachur, Ralph Hertwig, and Florian Steinmann. 2012. How do people judge risks: availability heuristic, affect heuristic, or both? Journal of Experimental Psychology: Applied, 18(3):314. find
  44. Shramay Palta, Nishant Balepur, Peter Rankel, Sarah Wiegreffe, Marine Carpuat, and Rachel Rudinger. 2024. Plausibly problematic questions in multiple-choice benchmarks for commonsense reasoning. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 3451–3473, Miami, Florida… find
  45. Shramay Palta and Rachel Rudinger. 2023. FORK: A bite-sized test set for probing culinary cultural biases in commonsense reasoning models. In Findings of the Association for Computational Linguistics: ACL 2023, pages 9952–9962, Toronto, Canada. Association for Computational Linguistics.
  46. Arjun Panickssery, Samuel R. Bowman, and Shi Feng. 2024. LLM evaluators recognize and favor their own generations. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. find
  47. Bhargavi Paranjape, Julian Michael, Marjan Ghazvininejad, Hannaneh Hajishirzi, and Luke Zettlemoyer. 2021. Prompting contrastive explanations for commonsense reasoning tasks. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 4179–4192, Online. Association for Compu… find
  48. Alicia Parrish, Harsh Trivedi, Ethan Perez, Angelica Chen, Nikita Nangia, Jason Phang, and Samuel Bowman. 2022. Single-turn debate does not help humans answer hard reading-comprehension questions. In Proceedings of the First Workshop on Learning with Natural Language Supervision, pages 17–28, Dublin… find
  49. Lianhui Qin, Vered Shwartz, Peter West, Chandra Bhagavatula, Jena D. Hwang, Ronan Le Bras, Antoine Bosselut, and Yejin Choi. 2020. Back to the future: Unsupervised backprop-based decoding for counterfactual and abductive commonsense reasoning. In Proceedings of the 2020 Conference on Empirical Metho…
  50. Nazneen Fatema Rajani, Bryan McCann, Caiming Xiong, and Richard Socher. 2019. Explain yourself! leveraging language models for commonsense reasoning. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4932–4942, Florence, Italy. Association for Computat…
  51. Melissa Roemmele, Cosmin Adrian Bejan, and Andrew S Gordon. 2011. Choice of plausible alternatives: An evaluation of commonsense causal reasoning. In 2011 AAAI Spring Symposium Series. find
  52. Rachel Rudinger, Vered Shwartz, Jena D. Hwang, Chandra Bhagavatula, Maxwell Forbes, Ronan Le Bras, Noah A. Smith, and Yejin Choi. 2020. Thinking like a skeptic: Defeasible inference in natural language. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4661–4675, Online… find
  53. Maarten Sap, Hannah Rashkin, Derek Chen, Ronan Le Bras, and Yejin Choi. 2019. Social IQa: Commonsense reasoning about social interactions. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processi… find
  54. Shlomi Sher and Craig RM McKenzie. 2008. Framing effects and rationality. The probabilistic mind: Prospects for Bayesian cognitive science, pages 79– 96. find
  55. Vered Shwartz, Peter West, Ronan Le Bras, Chandra Bhagavatula, and Yejin Choi. 2020. Unsupervised commonsense question answering with self-talk. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4615–4629, Online. Association for Computational L… find
  56. Chenglei Si, Navita Goyal, Tongshuang Wu, Chen Zhao, Shi Feng, Hal Daumé Iii, and Jordan Boyd-Graber. 2024. Large language models help humans verify truthfulness – except when they are convincingly wrong. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Comp… find
  57. Dirk D Steiner and Jeffrey S Rain. 1989. Immediate and delayed primacy and recency effects in performance evaluation. Journal of Applied Psychology, 74(1):136. find
  58. Alon Talmor, Jonathan Herzig, Nicholas Lourie, and Jonathan Berant. 2019. CommonsenseQA: A question answering challenge targeting commonsense knowledge. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,…
  59. Amos Tversky and Daniel Kahneman. 1973. Availability: A heuristic for judging frequency and probability. Cognitive Psychology, 5(2):207–232. find
  60. Su Wang, Greg Durrett, and Katrin Erk. 2018. Modeling semantic plausibility by injecting world knowledge. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 303–308, New Orl… find
  61. Mark E. Whiting and Duncan J. Watts. 2024. A framework for quantifying individual and collective common sense. Proceedings of the National Academy of Sciences, 121(4):e2309535121. find
  62. Sarah Wiegreffe, Jack Hessel, Swabha Swayamdipta, Mark Riedl, and Yejin Choi. 2022. Reframing human-AI collaboration for generating free-text explanations. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologie… find
  63. Sarah Wiegreffe and Ana Marasovic. 2021. Teach me to explain: A review of datasets for explainable natural language processing. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1). find
  64. Sarah Wiegreffe, Ana Marasović, and Noah A. Smith. 2021. Measuring association between labels and free-text rationales. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 10266–10284, Online and Punta Cana, Dominican Republic. Association for Computatio…
  65. Sheng Zhang, Rachel Rudinger, Kevin Duh, and Benjamin Van Durme. 2017. Ordinal common-sense inference. Transactions of the Association for Computational Linguistics, 5:379–395.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/palta-2026-arguments-that-alter-minds-llm/