Collaborative Disagreement Resolution for Scalable Oversight

Yuyang Jiang, Chacha Chen, Teng Wu, Liwen Sun, Han Liu, Shi Feng, Chenhao Tan
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:52111-52137, 2026.

Abstract

Debate, where AI agents argue opposing positions, has emerged as a key approach to scalable oversight. However, debate faces a fundamental tension: models are incentivized to be persuasive to the judge, which may not always align with epistemic honesty. In this work, we propose an alternative paradigm: disagreement resolution, which reframes the interaction mechanism from adversarial debate to collaborative truth seeking. Drawing on principles from human mediation and conflict resolution, where mediators facilitate dialogue to help disputing parties reach consensus rather than adjudicating between them, we design an automated pipeline that adapts these strategies to AI oversight. Unlike standard debate where models argue for fixed positions, our pipeline directs models to collaboratively identify points of disagreement, examine the evidence for conflicting claims, and converge toward consensus or isolate the specific ”crux” of their disagreement. We find that Disagreement Resolution consistently helps non-expert models identify the truth, achieving 62.1% judging accuracy compared to 49.2% for standard debate. Our results provide encouraging empirical evidence for rethinking the scalable oversight protocol from adversarial persuasion to collaborative truth-seeking.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-jiang26d, title = {Collaborative Disagreement Resolution for Scalable Oversight}, author = {Jiang, Yuyang and Chen, Chacha and Wu, Teng and Sun, Liwen and Liu, Han and Feng, Shi and Tan, Chenhao}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {52111--52137}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/jiang26d/jiang26d.pdf}, url = {https://proceedings.mlr.press/v306/jiang26d.html}, abstract = {Debate, where AI agents argue opposing positions, has emerged as a key approach to scalable oversight. However, debate faces a fundamental tension: models are incentivized to be persuasive to the judge, which may not always align with epistemic honesty. In this work, we propose an alternative paradigm: disagreement resolution, which reframes the interaction mechanism from adversarial debate to collaborative truth seeking. Drawing on principles from human mediation and conflict resolution, where mediators facilitate dialogue to help disputing parties reach consensus rather than adjudicating between them, we design an automated pipeline that adapts these strategies to AI oversight. Unlike standard debate where models argue for fixed positions, our pipeline directs models to collaboratively identify points of disagreement, examine the evidence for conflicting claims, and converge toward consensus or isolate the specific ”crux” of their disagreement. We find that Disagreement Resolution consistently helps non-expert models identify the truth, achieving 62.1% judging accuracy compared to 49.2% for standard debate. Our results provide encouraging empirical evidence for rethinking the scalable oversight protocol from adversarial persuasion to collaborative truth-seeking.} }
Endnote
%0 Conference Paper %T Collaborative Disagreement Resolution for Scalable Oversight %A Yuyang Jiang %A Chacha Chen %A Teng Wu %A Liwen Sun %A Han Liu %A Shi Feng %A Chenhao Tan %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-jiang26d %I PMLR %P 52111--52137 %U https://proceedings.mlr.press/v306/jiang26d.html %V 306 %X Debate, where AI agents argue opposing positions, has emerged as a key approach to scalable oversight. However, debate faces a fundamental tension: models are incentivized to be persuasive to the judge, which may not always align with epistemic honesty. In this work, we propose an alternative paradigm: disagreement resolution, which reframes the interaction mechanism from adversarial debate to collaborative truth seeking. Drawing on principles from human mediation and conflict resolution, where mediators facilitate dialogue to help disputing parties reach consensus rather than adjudicating between them, we design an automated pipeline that adapts these strategies to AI oversight. Unlike standard debate where models argue for fixed positions, our pipeline directs models to collaboratively identify points of disagreement, examine the evidence for conflicting claims, and converge toward consensus or isolate the specific ”crux” of their disagreement. We find that Disagreement Resolution consistently helps non-expert models identify the truth, achieving 62.1% judging accuracy compared to 49.2% for standard debate. Our results provide encouraging empirical evidence for rethinking the scalable oversight protocol from adversarial persuasion to collaborative truth-seeking.
APA
Jiang, Y., Chen, C., Wu, T., Sun, L., Liu, H., Feng, S. & Tan, C.. (2026). Collaborative Disagreement Resolution for Scalable Oversight. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:52111-52137 Available from https://proceedings.mlr.press/v306/jiang26d.html.

Related Material