Collaborative Disagreement Resolution for Scalable Oversight

• URL: http://arxiv.org/abs/2607.01251v1
• Date: Tue, 02 Jun 2026 12:55:49 GMT
• Title: Collaborative Disagreement Resolution for Scalable Oversight
• Abstract summary: Disagreement resolution helps non-expert models identify the truth, achieving 62.1% judging accuracy compared to 49.2% for standard debate.<n>Our results provide encouraging empirical evidence for rethinking the scalable oversight protocol from adversarial persuasion to collaborative truth-seeking.
• Score: 26.071237160687243
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Measuring AI Accountability Through Argumentation Analysis: Can Model Reasoning Withstand Scrutiny? [0.0]
  We investigate an alternative standard designed to function despite realistic ambiguity.<n>We use a four-phase dialectical protocol grounded in Walton's theory of argumentation schemes and Govier's criteria for argument cogency.<n>It is adaptive to different frames of reasoning, extends beyond multiple-choice framing, and treats both the reasoning that precedes a verdict and its post-hoc justification.
  arXiv  Detail & Related papers  (2026-09-04T12:40:39Z)
• ConflictScore: Identifying and Measuring How Language Models Handle Conflicting Evidence [48.938290419832335]
  We introduce ConflictScore, a novel metric that quantifies how well a model's response acknowledges conflicting evidence in its grounding documents.<n>Our framework decomposes responses into atomic claims, labels each claim against each grounding document, and then aggregates these labels into two complementary measures: ConflictScore-Count (CS-C), the proportion of claims exhibiting conflicts, and ConflictScore-Ratio (CS-R), the balance between supporting and contradicting evidence.
  arXiv  Detail & Related papers  (2026-06-24T23:00:09Z)
• Consensus is Strategically Insufficient: Reasoning-Trace Disagreement as a Knowledge-Representation Signal [0.0]
  Multi-agent systems are commonly designed to reduce disagreement through voting, consensus protocols, debate, or fault-tolerant aggregation.<n>We argue that this objective is insufficient for value-laden tasks, where disagreement may reflect genuine normative uncertainty rather than agent error.<n>We propose a knowledge-representation layer in which reasoning traces and agent decisions are abstracted into symbolic disagreement states.
  arXiv  Detail & Related papers  (2026-06-02T21:21:02Z)
• The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberation [68.98390038721963]
  We show that multi-agent discussion erases up to 72% of issue-critical facts.<n>This loss is consequential: retained evidence can reconstruct the issue misleadingly, final stances remain anchored in base-model priors, and a single malicious agent can inject misinformation into the shrinking shared context.<n>We call for evaluations that measure which facts, uncertainties, and legitimate disagreements survive interaction.
  arXiv  Detail & Related papers  (2026-06-02T02:15:40Z)
• GRASP: Deterministic argument ranking in interaction graphs [65.66879897437157]
  We show that holistic judging suffers from substantial inter-model disagreement.<n>This instability arises from collapsing a debate's complex interaction structure into a single opaque score.<n>We propose GRASP, a deterministic framework that aggregates stable local interaction judgments into a global ranking.
  arXiv  Detail & Related papers  (2026-05-18T21:49:02Z)
• Co-FactChecker: A Framework for Human-AI Collaborative Claim Verification Using Large Reasoning Models [99.26398772227684]
  We propose Co-FactChecker, a framework for human-AI collaborative claim verification.<n>Co-FactChecker translates expert feedback into trace-edits that introduce targeted modifications to the trace.<n>Human evaluations show that Co-FactChecker is preferred over multi-turn dialogue.
  arXiv  Detail & Related papers  (2026-04-15T10:35:00Z)
• When Contextual Inference Fails: Cancelability in Interactive Instruction Following [51.2195840589474]
  We introduce Build What I Mean, an interactive benchmark for contextual meaning construction.<n>In BWIM, models must resolve ambiguity by either performing a contextual inference or requesting clarification at a small communication cost.<n>We observe suboptimal strategies, such as partner-blind over-clarification and question-averse guessing under uncertainty.
  arXiv  Detail & Related papers  (2026-03-20T14:46:59Z)
• Knowledge Divergence and the Value of Debate for Scalable Oversight [0.0]
  Debate and reinforcement learning from AI feedback are proposed methods for scalable oversight of advanced AI systems.<n>We analyze this by parameterizing debate's value through the geometry of knowledge divergence between debating models.<n>We offer the first formal connection between debate and RLAIF, a geometric foundation for understanding when adversarial oversight protocols are justified.
  arXiv  Detail & Related papers  (2026-03-05T15:36:08Z)
• SAD: A Large-Scale Strategic Argumentative Dialogue Dataset [60.33125467375306]
  In practice, argumentation is often realized as multi-turn dialogue.<n>We present the first large-scale textbfStrategic textbfArgumentative textbfDialogue dataset, consisting of 392,822 examples.
  arXiv  Detail & Related papers  (2026-01-12T11:11:37Z)
• AI Debaters are More Persuasive when Arguing in Alignment with Their Own Beliefs [0.13525723298325706]
  We apply debate to subjective questions and explicitly measure large language models' prior beliefs before experiments.<n>We implement and compare two debate protocols, sequential and simultaneous, to evaluate potential systematic biases.<n>Our main findings show that models tend to prefer defending stances aligned with the judge persona rather than their prior beliefs.
  arXiv  Detail & Related papers  (2025-10-15T05:02:13Z)
• AI Debate Aids Assessment of Controversial Claims [73.8907110799657]
  We study whether AI debate can guide biased judges toward the truth by having two AI systems debate opposing sides of controversial factuality claims.<n>In Study I, debate consistently improves human judgment accuracy and confidence calibration, outperforming consultancy.<n>In Study II, AI judges with human-like personas achieve even higher accuracy (78.5%) than human judges (70.1%) and default AI judges without personas (69.8%)<n>These findings highlight AI debate as a promising path toward scalable, bias-resilient oversight in contested domains.
  arXiv  Detail & Related papers  (2025-06-02T19:01:53Z)
• From Argumentation to Deliberation: Perspectivized Stance Vectors for Fine-grained (Dis)agreement Analysis [17.184962277653902]
  We develop a framework for a deliberative analysis of arguments in a computational argumentation setup.<n>We conduct a fine-grained analysis of perspectivized stances expressed in the arguments of different arguers or stakeholders on a given issue.<n>We formalize this analysis in Perspectivized Stance Vectors that characterize the individual perspectivized stances of all arguers on a given issue.
  arXiv  Detail & Related papers  (2025-02-10T13:08:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.