arXiv AI
Jul 3
Collaborative Disagreement Resolution for Scalable Oversight
arXiv:2607. 01251v1 Announce Type: cross Abstract: Debate, where AI agents argue opposing positions, has emerged as a key approach to scalable oversight.
Humans Correct Their Judgments Through Debate, but Weaker AI Models Do Not
The paper examines whether AI‑driven debate can help humans and weaker language models (LLMs) correct their judgments. Experiments show that debate improves human accuracy over prior beliefs, especially with weighted voting, but offers little benefit—and sometimes harms—accuracy for weaker LLM supervisors. The study highlights debate as a promising tool for scalable human oversight while questioning its effectiveness for fully automated AI control.
Related stories
arXiv AI
Sep 10
Ordinary, Reasonable Chatbots: Do AI Models Track Human Legal Judgments?
The paper investigates whether large language model (LLM) chatbots can emulate human legal judgments of reasonableness. By comparing responses from 26 LLMs to those of human participants across 25 legal scenarios, the study finds that chatbots generally track human answers but tend to produce more homogeneous, government‑ and corporation‑friendly responses and align more closely with white, male, older, and more educated respondents. The authors note that these patterns warrant further systematic research.
arXiv AI
Jul 23
Avoiding Obfuscation with Prover-Estimator Debate
arXiv:2506. 13609v2 Announce Type: replace Abstract: Training powerful AI systems to exhibit desired behaviors hinges on the ability to provide accurate human supervision on increasingly complex tasks.
arXiv AI
Aug 20
A Theory of Post-hoc Debate Judgement
The paper proposes a theory for judging post-hoc debates in AI, focusing on properties like reproducibility, robustness, groundedness, and explainability. It evaluates two debate‑judgement methods—LLM judges and formal computational argumentation semantics—finding similar accuracy but noting that argumentation semantics offers stronger formal guarantees. The study suggests that argumentation semantics is a preferable framework for principled debate judges in AI systems.
arXiv AI
Sep 4
Toward Collective-Centric Evaluation of Preference Inference for Participatory Democracy
The paper examines how Preference Inference (PI) models used in large-scale participatory democracy platforms can alter the perceived consensus and minority support by predicting missing votes. It introduces a collective‑centric evaluation framework that assesses whether inferred votes maintain key properties of the overall preference landscape, rather than focusing solely on individual prediction accuracy. Using the largest multilingual dataset to date—four consultations with over 90,000 participants, 1 million votes, and 22 languages—the study finds that models with similar predictive accuracy can differ markedly in how well they preserve the collective structure, underscoring that accuracy alone is insufficient for evaluating PI in democratic contexts.
arXiv AI
Aug 13
Learning to Persuade Exposes How Easily LLMs Abandon Correct Beliefs
arXiv:2608. 11624v1 Announce Type: cross Abstract: Persuasion is a core dynamic of natural language communication, shaping how large language models (LLMs) update beliefs, resolve disagreements, and reach decisions.
arXiv AI
Oct 5
How to Have a Sensitive Debate: An Instance-Optimal Protocol for AI Debate
The paper introduces a new AI debate protocol that improves upon previous designs for problems with stable decompositions into subproblems. It guarantees correctness in a worst‑case sense, establishes honesty and correctness as a dominant‑strategy equilibrium for both debaters, and proves instance‑wise optimality through black‑box lower bounds. The authors connect stable problem decompositions to fractional block sensitivity from query complexity to achieve these results.
arXiv AI
Sep 10
How AI Models Manage Epistemic Authority: A Taxonomy and Comparative Analysis of Responses to User Disagreement
The paper introduces a taxonomy of six user challenge types and a four-layer framework to analyze how large language models respond to user disagreement. Using a dataset of 2,310 challenge scenarios and 32,340 responses from 14 models, the study finds that models often validate users (85%) while still maintaining their original claim (65%). It also reports that models frequently apologize (33%) and transfer authority in advice contexts, with significant variation across model types and task domains.
Hugging Face Trending Papers
Aug 12
Learning to Persuade Exposes How Easily LLMs Abandon Correct Beliefs
Persuasion is a core dynamic of natural language communication, shaping how large language models (LLMs) update beliefs, resolve disagreements, and reach decisions. As LLMs increasingly debate, advise, and think collaboratively with humans and each other, resistance to harmful persuasion becomes a core requirement for reliable behavior.
arXiv AI
Sep 7
MABPD: Multi-Agent Bias Probing & Detection via Structured Argument Debate
MABPD (Multi‑Agent Bias Probing & Detection) is a training‑free pipeline that uses three specialized large language model agents to analyze news articles from complementary perspectives and resolve disagreements via a Structured Argument Debate (SAD) protocol. SAD imposes an asymmetric burden of proof—biased claims lacking grounded textual evidence receive zero weight—along with role‑weighted voting and post‑consensus verification, replacing task‑specific supervised decision boundaries. Ablation studies show that the debate module alone accounts for up to a 10.6‑point F1 gain, and on the BABE benchmark MABPD attains 83.4% macro F1, within 0.7 percentage points of the supervised state‑of‑the‑art, while achieving 75.0% zero‑shot accuracy on the SemEval 2019 HyperPartisan corpus.
arXiv AI
Aug 12
The Deliberative Deficit: An Empirical Critique of LLMs in Democratic Discourse
arXiv:2608. 10186v1 Announce Type: cross Abstract: LLMs are increasingly deployed in settings that require collective reasoning on complex, value-laden problems.
arXiv AI
Sep 7
Measuring AI Accountability Through Argumentation Analysis: Can Model Reasoning Withstand Scrutiny?
The paper proposes a new method for evaluating AI accountability by analyzing the structural quality of a model’s defense for its decisions, using a four‑phase dialectical protocol based on Walton’s argumentation schemes and Govier’s criteria. Applied to nine large language models and 200 ambiguous moral-choice items, the study finds that models generally defend their reasoning well above the rubric minimum, though failures cluster on grounds and sufficiency and correlate with epistemic hedging. The protocol also reveals that models often present different argument schemes in justification than in reasoning, detects indefensible defenses, and highlights challenges in assessing retraction in AI alignment.