{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T09:04:09Z","timestamp":1773479049193,"version":"3.50.1"},"reference-count":38,"publisher":"Association for Computing Machinery (ACM)","issue":"1","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM J. Comput. Sustain. Soc."],"published-print":{"date-parts":[[2026,3,31]]},"abstract":"<jats:p>Conflict mediation requires reliably distinguishing the sources of disagreement as stemming from differences in beliefs about what is true (causality) vs. differences in what is valued (morality). The consequences of misdiagnosis -such as deadlock or escalation of conflict- can be significant, particularly in contexts related to sustainability and ethical management. Contributing to the rapidly developing literature on the use of Large Language Models (LLMs) to mediate contentious human discussions, we develop a conflict diagnosis competence test for LLMs to assess if they can differentiate disagreements rooted in causal and moral disagreements. We use a vignette study to apply the test to OpenAI\u2019s GPT-3.5 and GPT-4. We find that both LLMs have similar semantic understandings of the distinction between causal and evaluative (moral) sources of disagreement as humans and can reliably distinguish between them, with GPT-4 performing better than GPT-3.5. However, compared to humans, both models exhibit a tendency to overestimate the extent of causal disagreement and underestimate the extent of moral disagreement in situations that feature moral misalignment. We conclude by discussing the implications for using LLMs to mediate conflict.<\/jats:p>","DOI":"10.1145\/3771553","type":"journal-article","created":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T10:59:32Z","timestamp":1761562772000},"page":"1-32","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["LLMs as Mediators: Can They Diagnose Conflicts Accurately?"],"prefix":"10.1145","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6974-2382","authenticated-orcid":false,"given":"\u00d6zgecan","family":"Ko\u00e7ak","sequence":"first","affiliation":[{"name":"Emory University Goizueta Business School","place":["Atlanta, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0032-8538","authenticated-orcid":false,"given":"Phanish","family":"Puranam","sequence":"additional","affiliation":[{"name":"INSEAD Asia Campus","place":["Singapore, Singapore"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8932-5642","authenticated-orcid":false,"given":"Af\u015far","family":"Yegin","sequence":"additional","affiliation":[{"name":"Kadir Has University","place":["Istanbul, T\u00fcrkiye"]}]}],"member":"320","published-online":{"date-parts":[[2026,3,14]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2311627120"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-32711-4"},{"key":"e_1_3_2_4_2","first-page":"38176","volume-title":"Proceedings of the Advances in Neural Information Processing Systems.","volume":"35","author":"Bakker Michiel","year":"2022","unstructured":"Michiel Bakker, Martin Chadwick, Hannah Sheahan, Michael Tessler, Lucy Campbell-Gillingham, Jan Balaguer, Nat McAleese, Amelia Glaese, John Aslanides, Matt Botvinick, et\u00a0al. 2022. Fine-tuning language models to find agreement among humans with diverse preferences. In Proceedings of the Advances in Neural Information Processing Systems.S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35, Curran Associates, Inc., 38176\u201338189. Retrieved from https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/f978c8f3b5f399cae464e85f72e28503-Paper-Conference.pdf"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1037\/0021-9010.93.1.170"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-023-01582-0"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713757"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714934"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1037\/0021-9010.88.4.741"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1037\/a0024844"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-86510-0"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2023.04.008"},{"key":"e_1_3_2_13_2","first-page":"179","volume-title":"Cross-cultural Research Methods in Psychology","author":"Fischer R.","year":"2011","unstructured":"R. Fischer and J. R. J. Fontaine. 2011. Methods for investigating structural equivalence. In Cross-cultural Research Methods in Psychology, D. Matsumoto and F. J. R. van de Vijver (Eds.). Cambridge University Press, Cambridge, UK, 179\u2013215."},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2019.01507"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3670865.3673547"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642322"},{"key":"e_1_3_2_17_2","first-page":"209","volume-title":"Proceedings of the A New Look on Intuition in Judgment and Decision Making.","author":"Haidt J.","year":"2007","unstructured":"J. Haidt and S. Kesebir. 2007. In the forest of value: Why moral intuitions are different from other kinds. In Proceedings of the A New Look on Intuition in Judgment and Decision Making.H. Plessner, C. Betsch, and T. Betsch (Eds.), Lawrence Erlbaum Associates, New York, NY, USA, 209\u2013229."},{"key":"e_1_3_2_18_2","volume-title":"Multivariate Data Analysis (7th ed.)","author":"Hair J. F.","year":"2010","unstructured":"J. F. Hair, W. C. Black, B. J. Babin, and R. E. Anderson. 2010. Multivariate Data Analysis (7th ed.). Pearson, New York."},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1002\/smj.3181"},{"key":"e_1_3_2_20_2","unstructured":"G. A. Huber J. J. Cho S. E. Bokemper A. S. Gerber W. J. Brady K. McLoughlin and M. J. Crockett. 2023. Fact-Value Disagreements about Threats to Electoral Integrity: Beliefs about the Importance and Prevalence of Fraudulent Uncounted and Foregone Votes in the 2020 Election. Retrieved from https:\/\/johnjcho.com\/papers\/election_integrity\/Election_Integrity_Unblinded_Submission.pdfWorking Paper."},{"key":"e_1_3_2_21_2","unstructured":"JASP Team. 2024. JASP (Version 0.18.3). Retrieved from https:\/\/jasp-stats.org\/[Computer Software]."},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.2307\/3069453"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732022"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1287\/stsc.2022.0008"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2023.1166023"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2309350120"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1002\/job.4030130303"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1080\/13504509.2020.1859415"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3670691"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.21500\/20112084.857"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tsc.2013.01.002"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF01405730"},{"key":"e_1_3_2_33_2","unstructured":"Rupak Sarkar Neha Srikanth Taylor Hudson Rachel Rudinger Claire Bonial and Philip Resnik. 2025. Understanding Common Ground Misalignment in Goal-Oriented Dialog: A Case-Study with Ubuntu Chat Logs. arxiv:2503.12370. Retrieved from https:\/\/arxiv.org\/abs\/2503.12370"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642159"},{"key":"e_1_3_2_35_2","unstructured":"Christopher T. Small Ivan Vendrov Esin Durmus Hadjar Homaei Elizabeth Barry Julien Cornebise Ted Suzman Deep Ganguli and Colin Megill. 2023. Opportunities and Risks of LLMs for Scalable Deliberation with Polis. arxiv:2306.11932. Retrieved from https:\/\/arxiv.org\/abs\/2306.11932"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-024-01882-z"},{"key":"e_1_3_2_37_2","unstructured":"Jinzhe Tan Hannes Westermann Nikhil Reddy Pottanigari Jarom\u00edr \u0160avelka S\u00e9bastien Mee\u00f9s Mia Godet and Karim Benyekhlef. 2024. Robots in the Middle: Evaluating LLMs in Dispute Resolution. arxiv:2410.07053. Retrieved from https:\/\/arxiv.org\/abs\/2410.07053"},{"issue":"6719","key":"e_1_3_2_38_2","doi-asserted-by":"crossref","DOI":"10.1126\/science.adq2852","article-title":"AI can help humans find common ground in democratic deliberation","volume":"386","author":"Tessler M. H.","year":"2024","unstructured":"M. H. Tessler, M. A. Bakker, D. Jarrett, H. Sheahan, M. J. Chadwick, R. Koster, others, and C. Summerfield. 2024. AI can help humans find common ground in democratic deliberation. Science 386, 6719 (2024), eadq2852.","journal-title":"Science"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2309535121"}],"container-title":["ACM Journal on Computing and Sustainable Societies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3771553","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T08:46:28Z","timestamp":1773477988000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3771553"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,3,31]]}},"alternative-id":["10.1145\/3771553"],"URL":"https:\/\/doi.org\/10.1145\/3771553","relation":{},"ISSN":["2834-5533"],"issn-type":[{"value":"2834-5533","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,14]]},"assertion":[{"value":"2025-03-17","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-16","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}