{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T18:45:00Z","timestamp":1782758700131,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,25]]},"DOI":"10.1145\/3805689.3806447","type":"proceedings-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T17:52:08Z","timestamp":1782755528000},"page":"7327-7372","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["The Fragility of Moral Judgment in Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8357-2316","authenticated-orcid":false,"given":"Tom","family":"van Nuenen","sequence":"first","affiliation":[{"name":"D-Lab, University of California, Berkeley, Berkeley, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6809-2437","authenticated-orcid":false,"given":"Pratik Singh","family":"Sachdeva","sequence":"additional","affiliation":[{"name":"D-Lab, University of California, Berkeley, Berkeley, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,25]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Asad Aali Muhammad Ahmed Mohsin Vasiliki Bikia Arnav Singhvi Richard Gaus Suhana Bedi Hejie Cui Miguel Fuentes Alyssa Unell Yifan Mai Jordan Cahoon Michael Pfeffer Roxana Daneshjou Sanmi Koyejo Emily Alsentzer Christopher Potts Nigam H. Shah and Akshay S. Chaudhari. 2025. Structured Prompts Improve Evaluation of Language Models. arXiv:2511.20836 [cs.CL] https:\/\/arxiv.org\/abs\/2511.20836"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.982"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746059.3747740"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3701716.3715578"},{"key":"e_1_3_2_1_5_1","unstructured":"Juan Miguel Navarro Carranza. 2025. LLMs Show Surface-Form Brittleness Under Paraphrase Stress Tests. arXiv:2510.08616 [cs.CL] https:\/\/arxiv.org\/abs\/2510.08616"},{"key":"e_1_3_2_1_6_1","volume-title":"Carl Yan Shan, and Kevin Wadman","author":"Chatterji Aaron","year":"2025","unstructured":"Aaron Chatterji, Thomas Cunningham, David J Deming, Zoe Hitzig, Christopher Ong, Carl Yan Shan, and Kevin Wadman. 2025. How people use chatgpt. Technical Report. National Bureau of Economic Research."},{"key":"e_1_3_2_1_7_1","unstructured":"Manav Chaudhary Harshit Gupta Savita Bhat and Vasudeva Varma. 2024. Towards Understanding the Robustness of LLM-based Evaluations under Perturbations. arXiv:2412.09269 [cs.CL] https:\/\/arxiv.org\/abs\/2412.09269"},{"key":"e_1_3_2_1_8_1","unstructured":"Zhi-Yuan Chen Hao Wang Xinyu Zhang Enrui Hu and Yankai Lin. 2025. Beyond the Surface: Measuring Self-Preference in LLM Judgments. arXiv:2506.02592 [cs.CL] https:\/\/arxiv.org\/abs\/2506.02592"},{"key":"e_1_3_2_1_9_1","volume-title":"ELEPHANT: Measuring and understanding social sycophancy in LLMs. arXiv:2505.13995 [cs.CL] https:\/\/arxiv.org\/abs\/2505.13995","author":"Cheng Myra","year":"2025","unstructured":"Myra Cheng, Sunny Yu, Cinoo Lee, Pranav Khadpe, Lujain Ibrahim, and Dan Jurafsky. 2025. ELEPHANT: Measuring and understanding social sycophancy in LLMs. arXiv:2505.13995 [cs.CL] https:\/\/arxiv.org\/abs\/2505.13995"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2412015122"},{"key":"e_1_3_2_1_11_1","unstructured":"Yu Ying Chiu Liwei Jiang and Yejin Choi. 2025. DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life. arXiv:2410.02683 [cs.CL] https:\/\/arxiv.org\/abs\/2410.02683"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Jiwon Chun Gefei Zhang and Meng Xia. 2025. ConflictLens: LLM-Based Conflict Resolution Training in Romantic Relationship. arXiv:2505.11715 [cs.HC] https:\/\/arxiv.org\/abs\/2505.11715","DOI":"10.1145\/3746058.3758422"},{"key":"e_1_3_2_1_13_1","unstructured":"Davi Bastos Costa Felippe Alves and Renato Vicente. 2025. Moral Susceptibility and Robustness under Persona Role-Play in Large Language Models. arXiv:2511.08565 [cs.CL] https:\/\/arxiv.org\/abs\/2511.08565"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-86510-0"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1177\/1088868318811759"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.73"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aies.v8i1.36598"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/0895-4356(90)90158-L"},{"key":"e_1_3_2_1_19_1","unstructured":"Mohammad Fraiwan and Natheer Khasawneh. 2023. A Review of ChatGPT Applications in Education Marketing Software Engineering and Healthcare: Benefits Drawbacks and Research Directions. arXiv:2305.00237 [cs.CY] https:\/\/arxiv.org\/abs\/2305.00237"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e38056"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715318.3715327"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-18489-7"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.606"},{"key":"e_1_3_2_1_24_1","first-page":"23","article-title":"A Comparison of Guilt and Shame as Moral Motivators in Decision-making","volume":"52","author":"Knez Igor","year":"2017","unstructured":"Igor Knez and Olle Nordhall. 2017. A Comparison of Guilt and Shame as Moral Motivators in Decision-making. Journal of Environmental Psychology 52 (2017), 23\u201331.","journal-title":"Journal of Environmental Psychology"},{"key":"e_1_3_2_1_25_1","unstructured":"Lorenz Kuhn Yarin Gal and Sebastian Farquhar. 2023. Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation. In The Eleventh International Conference on Learning Representations. OpenReview.net Kigali Rwanda. ICLR 2023."},{"key":"e_1_3_2_1_26_1","unstructured":"Philippe Laban Lidiya Murakhovs'ka Caiming Xiong and Chien-Sheng Wu. 2024. Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experiment. arXiv:2311.08596 [cs.CL] https:\/\/arxiv.org\/abs\/2311.08596"},{"key":"e_1_3_2_1_27_1","volume-title":"Peter Railton, and Lu Wang.","author":"Lee Ayoung","year":"2025","unstructured":"Ayoung Lee, Ryan Sungmo Kwon, Peter Railton, and Lu Wang. 2025. CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectives. arXiv:2504.10823 [cs.CL] https:\/\/arxiv.org\/abs\/2504.10823"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.winlp-main.10"},{"key":"e_1_3_2_1_29_1","volume-title":"Rogerio Abreu de Paula, Marcelo Carpinette Grave, Aminat Adebiyi, Luan Soares de Souza, Enrico Santarelli, and Claudio Pinhanez.","author":"Machado Tiago","year":"2025","unstructured":"Tiago Machado, Maysa Malfiza Garcia de Macedo, Rogerio Abreu de Paula, Marcelo Carpinette Grave, Aminat Adebiyi, Luan Soares de Souza, Enrico Santarelli, and Claudio Pinhanez. 2025. A methodological analysis of prompt perturbations and their effect on attack success rates. arXiv:2511.10686 [cs.CL] https:\/\/arxiv.org\/abs\/2511.10686"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1224"},{"key":"e_1_3_2_1_31_1","volume-title":"Griffiths","author":"McCoy R. Thomas","year":"2023","unstructured":"R. Thomas McCoy, Shunyu Yao, Dan Friedman, Matthew Hardy, and Thomas L. Griffiths. 2023. Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve. arXiv:2309.13638 [cs.CL] https:\/\/arxiv.org\/abs\/2309.13638"},{"key":"e_1_3_2_1_32_1","unstructured":"Simon M\u00fcnker. 2025. Cultural Bias in Large Language Models: Evaluating AI Agents through Moral Questionnaires. arXiv:2507.10073 [cs.CL] https:\/\/arxiv.org\/abs\/2507.10073"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Afrozah Nadeem Mark Dras and Usman Naseem. 2025. Steering Towards Fairness: Mitigating Political Bias in LLMs. arXiv:2508.08846 [cs.CL] https:\/\/arxiv.org\/abs\/2508.08846","DOI":"10.26615\/978-954-452-099-1-006"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsos.241229"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2197"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.15781\/T29G6Z"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732044"},{"key":"e_1_3_2_1_38_1","volume-title":"Sachdeva and Tom van Nuenen","author":"Pratik","year":"2025","unstructured":"Pratik S. Sachdeva and Tom van Nuenen. 2025. Deliberative Dynamics and Value Alignment in LLM Debates. arXiv:2510.10002 [cs.AI] https:\/\/arxiv.org\/abs\/2510.10002"},{"key":"e_1_3_2_1_39_1","volume-title":"The Twelfth International Conference on Learning Representations. OpenReview.net","author":"Sclar Melanie","year":"2024","unstructured":"Melanie Sclar, Yejin Choi, Yulia Tsvetkov, and Alane Suhr. 2024. Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I Learned to Start Worrying about Prompt Formatting. In The Twelfth International Conference on Learning Representations. OpenReview.net, Vienna, Austria. ICLR 2024."},{"key":"e_1_3_2_1_40_1","volume-title":"Towards Understanding Sycophancy in Language Models. In The Twelfth International Conference on Learning Representations. OpenReview.net","author":"Sharma Mrinank","year":"2024","unstructured":"Mrinank Sharma, Meg Tong, Tomasz Korbak, David Duvenaud, Amanda Askell, Samuel R. Bowman, Newton Cheng, Esin Durmus, Zac Hatfield-Dodds, Scott R. Johnston, Shauna Kravec, Timothy Maxwell, Sam McCandlish, Kamal Ndousse, Oliver Rausch, Nicholas Schiefer, Da Yan, Miranda Zhang, and Ethan Perez. 2024. Towards Understanding Sycophancy in Language Models. In The Twelfth International Conference on Learning Representations. OpenReview.net, Vienna, Austria. arXiv:2310.13548 [cs.CL] https:\/\/openreview.net\/forum?id=tvhaxkMKAn ICLR 2024."},{"key":"e_1_3_2_1_41_1","unstructured":"Jiayuan Su Jing Luo Hongwei Wang and Lu Cheng. 2024. API Is Enough: Conformal Prediction for Large Language Models Without Logit-Access. arXiv:2403.01216 [cs.CL] https:\/\/arxiv.org\/abs\/2403.01216"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsos.231393"},{"key":"e_1_3_2_1_43_1","volume-title":"Sachdeva","author":"van Nuenen Tom","year":"2026","unstructured":"Tom van Nuenen and Pratik S. Sachdeva. 2026. Code for The Fragility of Moral Judgment in Large Language Models. https:\/\/github.com\/dlab-projects\/fragility-moral-judgment-llms. GitHub repository accompanying the FAccT 2026 paper."},{"key":"e_1_3_2_1_44_1","volume-title":"Sachdeva","author":"van Nuenen Tom","year":"2026","unstructured":"Tom van Nuenen and Pratik S. Sachdeva. 2026. Dataset for The Fragility of Moral Judgment in Large Language Models. https:\/\/huggingface.co\/datasets\/ucberkeley-dlab\/fragility-moral-judgment-llms. Dataset accompanying the FAccT 2026 paper."},{"key":"e_1_3_2_1_45_1","first-page":"449","article-title":"A Meta-analytic Review of Valence Framing Effects in Moral Decision-making","volume":"10","author":"Walasek Lukasz","year":"2015","unstructured":"Lukasz Walasek and Neil Stewart. 2015. A Meta-analytic Review of Valence Framing Effects in Moral Decision-making. Judgment and Decision Making 10, 5 (2015), 449\u2013458.","journal-title":"Judgment and Decision Making"},{"key":"e_1_3_2_1_46_1","volume-title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models. In The Eleventh International Conference on Learning Representations. OpenReview.net, Kigali, Rwanda. ICLR","author":"Wang Xuezhi","year":"2023","unstructured":"Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023. Self-Consistency Improves Chain of Thought Reasoning in Language Models. In The Eleventh International Conference on Learning Representations. OpenReview.net, Kigali, Rwanda. ICLR 2023."},{"key":"e_1_3_2_1_47_1","unstructured":"Koki Wataoka Tsubasa Takahashi and Ryokan Ri. 2025. Self-Preference Bias in LLM-as-a-Judge. arXiv:2410.21819 [cs.CL] https:\/\/arxiv.org\/abs\/2410.21819"},{"key":"e_1_3_2_1_48_1","unstructured":"Tianhao Wu Janice Lan Weizhe Yuan Jiantao Jiao Jason Weston and Sainbayar Sukhbaatar. 2024. Thinking LLMs: General Instruction Following with Thought Generation. arXiv:2410.10630 [cs.CL] https:\/\/arxiv.org\/abs\/2410.10630"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00146-025-02225-w"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"crossref","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zi Lin Zhuohan Li Dacheng Li Eric P. Xing Hao Zhang Joseph E. Gonzalez and Ion Stoica. 2023. Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena. arXiv:2306.05685 [cs.CL] https:\/\/arxiv.org\/abs\/2306.05685","DOI":"10.52202\/075280-2020"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.108"}],"event":{"name":"FAccT '26: The 2026 ACM Conference on Fairness, Accountability, and Transparency","location":"Montreal QC Canada","acronym":"FAccT '26","sponsor":["ACM\/SIG"]},"container-title":["Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3805689.3806447","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T17:54:29Z","timestamp":1782755669000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805689.3806447"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,25]]},"references-count":51,"alternative-id":["10.1145\/3805689.3806447","10.1145\/3805689"],"URL":"https:\/\/doi.org\/10.1145\/3805689.3806447","relation":{},"subject":[],"published":{"date-parts":[[2026,6,25]]},"assertion":[{"value":"2026-06-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}