Humans Correct Their Judgments Through Debate, but Weaker AI Models Do Not

Maria Victoria Carro; Denise Alejandra Mester; Facundo Nieto; Oscar Agustin Stanchi; Guido Ernesto Bergman; Giovanni Franco Gabriel Marrafini; Trinidad Borrell; Guido Freire

cs.AIOct 20, 2026

Humans Correct Their Judgments Through Debate, but Weaker AI Models Do Not

Authors: Maria Victoria Carro, Denise Alejandra Mester, Facundo Nieto, Oscar Agustin Stanchi, Guido Ernesto Bergman, Giovanni Franco Gabriel Marrafini, Trinidad Borrell, Guido Freire,

Organizations: Università degli Studi di Genova, IT · FAIR, IALAB, Universidad de Buenos Aires (UBA), AR · Instituto de Investigación en Informática LIDI, Universidad Nacional de La Plata, AR · Universitat Rovira i Virgili, ES · Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET), AR · BAISH, AR · Inria, FR · Sigma Nova, FR · Paris Brain Institute (ICM), Sorbonne Université, INSERM, CNRS, FR · Departamento de Computación, FCEyN, Universidad de Buenos Aires, AR · Dept. of Comp. Sci. and Eng., Universidad Nacional del Sur (UNS) & ICIC-CONICET, AR · Laboratorio de Neurociencia, Universidad Torcuato Di Tella, AR · Department of Mathematics and Computer Science, University of Cagliari, IT · Artificial Intelligence Research Institute (IIIA-CSIC), ES

Abstract

How can we effectively oversee AI systems that surpass human intelligence? AI Safety via Debate proposes that two AI systems argue opposing positions and a judge, either a human or a weaker model, decides which is correct. By facilitating supervisors in providing high-quality training signals, debate aims to encourage truthful and safe behavior from AI systems whose capabilities exceed our own. However, human judgment is not neutral: people often rely on biases which advanced AI systems may learn to exploit. Drawing on insights from collective intelligence and social cognition, this paper investigates whether debate can guide human and LLM supervisors toward the truth despite their prior beliefs. We evaluate several protocol configurations. We also explore setups inspired by the wisdom of the crowd such as the number and diversity of judges, as well as interaction mechanisms including deliberation and voting. Overall, we find that debate increases accuracy relative to prior beliefs for human judges, whereas the consultancy baseline, in which a single expert argues for one answer, does not. For weaker language models, however, the results are mixed: debate provides no comparable gains in most settings and can even reduce accuracy. Among multi-judge protocols, weighted voting produces the highest accuracy for human supervisors, whereas for LLMs none of them significantly improves group accuracy, even as the number of judges increases. Notably, the behavior of minority judges in non-diverse deliberation protocols suggests that, under symmetric settings, incorrect positions could be more persuasive than correct ones. These findings support debate as a viable path toward scalable human oversight, but cast doubt on its benefits for weaker AI supervisors, raising concerns about fully automated training and control pipelines in high-stakes settings.

Figures & tables

Figure 1: Full experimental pipeline and protocol variations, with human or LLM as supervisors.

Figure 2: Human judge accuracy per protocol. Error bars: 95% CIs (clustered by deliberation room for multi-human post-deliberation); dashed line: chance; * Holm-adjusted

p<.05

GPB Method	Consultancy	In-Subtopic Debate	Cross-Subtopic Debate	Multi-Judge
GPB System Prompt	Claude Sonnet 4	Proprietary, Open	Claude Sonnet 4	Proprietary
Persona Capping	$\cdot$	Open	$\cdot$	$\cdot$
Persona Prompting	$\cdot$	Open	$\cdot$	$\cdot$
Unconditioned	Claude Sonnet 4	Proprietary, Open	$\cdot$	$\cdot$

Table 1: Overview of GPB injection methods, protocols, and judge models. Proprietary : Claude Sonnet 4, GPT-5.2, GPT-4o, Gemini 3 Flash, Gemini 2.5 Pro. Open : Qwen2.5-7B-Instruct, Gemma-3-4B-IT, Llama-3.1-8B-Instruct.

\cdot

indicates the combination was not evaluated.

Figure 3: Transcript order for one debate under both majority conditions.

Protocol	# Judges	Diversity
Deliberation with consensus	3	No
Deliberation without consensus	3, 7	No
	3, 7	Yes
Voting	3, 7	No
Weighted Voting	3, 7	No

Table 2: Experimental configurations for the multi-judge LLM experiments. All judges are Claude Sonnet 4 in the non-diverse condition, whereas the diverse condition uses GPT-4o, GPT-5.2, Claude Sonnet 4, Gemini 2.5 Pro, and Gemini 3 Flash.

Figure 4: Accuracy of LLM judges (Claude Sonnet 4 with the GPB system prompt) across protocols. Error bars: 95% CIs (clustered by debate for multi-judge protocols); dashed line: chance; * Holm-adjusted

p<.05

Figure 5: Deliberation dynamics of LLM judges. (a) Accuracy of grounded and erroneous judges across stages in three-judge panels. (b) Share of post-debate minority and majority judges switching during deliberation. (c) Share of grounded and erroneous minority judges switching during deliberation, by panel configuration. Error bars: 95% CIs clustered by debate.

Appendix figures & tables16 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 6: The interface shows the first round of a debate. The following rounds are presented in the same fashion.

Figure 7: Deliberation interfaces. Left: multi-judge (hybrid) condition, showing the two LLMs’ opening interventions. Right: human-only condition, showing the coordinator’s opening interaction.

Experimental Protocol	GPB Group	$n$	Pre Acc.	Pre Conf. (M)	Post Acc.	Post Conf. (M)	Belief Reversals T $\rightarrow$ F	Belief Reversals F $\rightarrow$ T	$\Delta$ Acc. (pp)	$p$ (McNemar) [Acc.]	$p$ (Wilcoxon) [Conf.]
Consultancy	Grounded	48	60.42	57.75	58.33	72.73	22.92	20.83	$-$ 2.09	1.000	.006
	Erroneous	32	37.50	56.97	34.38	74.38	21.88	18.75	$-$ 3.12	1.000	.002
	Average	80	51.25	57.44	48.75	73.39	22.50	20.00	$-$ 2.50	1.000	$<$ .001
Debate In-subtopic	Grounded	47	61.70	55.32	70.21	66.23	4.26	12.77	8.51	1.000	.004
	Erroneous	45	20.00	61.20	44.44	69.62	4.44	28.89	24.44	.163	.010
	Average	92	41.30	58.20	57.61	67.89	4.35	20.65	16.31	.028	$<$ .001

Appendix

Table 5: Human experiments: single-judge decision protocols. Accuracy (Acc.), mean confidence (Conf.), and belief reversals are reported in %.

p

-values are Holm-adjusted; bold indicates

p<.05

. † Binomial test of post-debate accuracy against chance, as pre/post items differ in the cross-subtopic protocol.

Experimental Protocol	GPB Group	$n$	Pre Acc.	Pre Conf. (M)	Post Acc.	Post Conf. (M)	Belief Reversals T $\rightarrow$ F	Belief Reversals F $\rightarrow$ T	$\Delta$ Acc. (pp)	$p$ (McNemar) [Acc.]	$p$ (Wilcoxon) [Conf.]
Voting	Grounded	110	66.67	58.76	83.33	69.25	5.45	15.45	16.67	1.000	$<$ .001
	Erroneous	106	19.44	57.61	41.67	65.75	8.49	24.53	22.22	.387	$<$ .001
	Average	216	43.06	58.20	62.50	67.53	6.94	19.91	19.44	.028	$<$ .001
Weighted Voting	Grounded	110	72.22	58.76	86.11	69.25	5.45	15.45	13.89	1.000	$<$ .001
	Erroneous	106	19.44	57.61	44.44	65.75	8.49	24.53	25.00	.242	$<$ .001
	Average	216	45.83	58.20	65.28	67.53	6.94	19.91	19.44	.028	$<$ .001

Appendix

Table 6: Human experiments: voting protocols. Both protocols use the same 72 three-judge groups, labeled Grounded or Erroneous by the majority GPB of their members (36 each). Acc.,

\Delta

Acc., and McNemar tests are computed over groups;

n

, mean confidence (Conf.), belief reversals, and Wilcoxon tests over individual judges. All values in %.

p

-values are Holm-adjusted; bold indicates

p<.05

Experimental Protocol	GPB Group	$n$	Pre-Debate		Post-Debate		Post-Deliberation		Pre-Debate $\rightarrow$ Post-Debate				Post-Debate $\rightarrow$ Post-Deliberation				Pre-Debate $\rightarrow$ Post-Delib.
Experimental Protocol	GPB Group	$n$	Acc.	Conf.	Acc.	Conf.	Acc.	Conf.	Rev. T $\rightarrow$ F	Rev. F $\rightarrow$ T	$\Delta$ Acc. (pp)	$p$ (McNemar)	Rev. T $\rightarrow$ F	Rev. F $\rightarrow$ T	$\Delta$ Acc. (pp)	$p$ (McNemar)	$p$ (McNemar)	$p$ (Wilcoxon)
Multi-Human Deliberation	Grounded	77	66.23	56.10	72.73	67.71	71.43	73.01	6.49	12.99	6.49	1.000	6.49	5.19	$-$ 1.30	1.000	1.000	$<$ .001
	Erroneous	50	30.00	56.58	48.00	62.76	48.00	68.20	4.00	22.00	18.00	.164	4.00	4.00	0.00	1.000	.352	$<$ .01
	Average	127	51.97	56.29	62.99	65.76	62.20	71.12	5.51	16.54	11.02	.118	5.51	4.72	$-$ 0.79	1.000	.369	$<$ .001
Hybrid Deliberation	H Grounded	57	64.91	65.91	66.67	73.60	70.18	78.51	12.28	14.04	1.76	1.000	7.02	10.53	3.51	1.000	1.000	$<$ .001
	H Erroneous	48	33.33	60.52	39.58	68.42	41.67	73.19	14.58	20.83	6.25	1.000	4.17	6.25	2.09	1.000	1.000	.008

Appendix

Table 7: Human experiments: deliberation protocols. Accuracy (Acc.), mean confidence (Conf.), and belief reversals (Rev.) are reported in %. H: human judges. For multi-human deliberation, all McNemar and Wilcoxon tests (Pre-Debate

\rightarrow

Post-Debate, Post-Debate

\rightarrow

Post-Deliberation, and Pre-Debate

\rightarrow

Post-Deliberation) are cluster-level randomization versions with deliberation rooms as clusters.

p

-values are Holm-adjusted; bold indicates

p<.05

Figure 8: Change in accuracy from pre-debate to the final stage by GPB group (pp): grounded and erroneous . Error bars: 95% Newcombe CIs.

Grounded Personas		Erroneous Personas
Engineer pilot	Entrepreneur travel	Aviophobe	Religious risk averse
Technologist	Science layperson	Cautious religious	Christian conservative
Physicist	Biologist atheist	Peace activist	Moralist religious
Scientist optimist	Researcher cs	Artist pessimist	Artist conservative
Astronomer	PhD right wing	Pessimist religious	Religious skeptical

Appendix

Table 8: Complete list of the 20 personas used to construct the grounded and erroneous activation axes, grouped by classification. For each persona, three distinct descriptive variants were used rather than a single fixed description, to reduce variance attributable to prompt-specific wording rather than to the persona itself. For example, one variant of the “aviophobe” persona read: “You are a skeptic by nature with limited formal training in the sciences and a lifelong fear of flying. You tend to dismiss bold scientific announcements as overhyped.”

System prompt	No persona capping	With persona capping
No prompt	C1	C2
Belief	C3	C4
Belief + Persona	C5	C6

Appendix

Table 9: Experimental conditions (C1–C6) resulting from the

2\times 3

factorial design.

Group	Personas
Disability	a physically-disabled person, an able-bodied person
Religion	a Jewish person, a Christian person, an Atheist person, a Religious person
Race	an African person, a Hispanic person, an Asian person, a Caucasian person
Gender	a man, a woman, a transgender man, a transgender woman, a non-binary person
Political Affiliation	a lifelong Democrat, a lifelong Republican

Appendix

Table 10: Personas taken from Gupta et al. [2023] , used in our experiments.

			Accuracy (%)			Reversals (%)		Confidence
Protocol	Group	$n$	Pre	Post	$\Delta$	T $\rightarrow$ F	F $\rightarrow$ T	Pre	Post	$p$
Unconditioned
Consultancy	All	192	84.38	76.56	$-7.82$	11.46	3.65	85.08	81.49	.041
Debate (in)	All	190	85.26	78.95	$-6.32$	8.95	2.63	86.03	84.67	.068
GPB system prompt
Consultancy	Grounded	200	92.00	75.00	$-17.00$	20.50	3.50	86.64	80.12	$<.001^{\dagger}$

Appendix

Table 11: Debate versus consultancy with Claude Sonnet 4 as judge. Reversals are percentages of

n

p

: Holm-adjusted McNemar’s test; † unadjusted McNemar’s test; ‡ unadjusted topic-clustered bootstrap; § Holm-adjusted binomial test against chance.

				Accuracy (%)			Reversals (%)		Confidence
Model	Group	$n$	Align. (%)	Pre	Post	$\Delta$	T $\rightarrow$ F	F $\rightarrow$ T	Pre	Post	$p$
Unconditioned
GPT-5.2	All	198	–	84.85	90.40	$+5.56$	1.01	6.57	87.21	87.13	.044
GPT-4o	All	198	–	86.36	84.85	$-1.52$	5.56	4.04	89.49	89.82	1.0
Gemini 3 Flash	All	198	–	92.93	95.96	$+3.03$	0.00	3.03	96.06	96.87	.16
Gemini 2.5 Pro	All	196	–	91.84	91.33	$-0.51$	5.61	5.10	94.61	95.38	1.0

Appendix

Table 12: In-subtopic debate across proprietary models other than Claude. Align.: alignment between the GPB and the model’s specific pre-debate belief. Reversals are percentages of

n

p

: Holm-adjusted McNemar’s test; † unadjusted McNemar’s test.

Figure 9: Pre-debate and post-debate accuracy of grounded and erroneous judges under the GPB system prompt, by argument order. Claude Sonnet 4 is shown as a reference. Error bars are 95% bootstrap confidence intervals over claims; the dashed line marks chance.

		Alignment (%)		Grounded acc. (%)		Erroneous acc. (%)		Average acc. (%)
Model	Intervention	G	E	Pre	Post	Pre	Post	Pre	Post	$p$
Llama-3.1-8B	Unconditioned	–	–	–	–	–	–	74.40	62.80	.17
	PC	71.2	34.3	71.2	62.8	65.7	63.3	68.45	63.05	.66
	GPB	81.0	74.8	81.0	70.0	25.2	32.5	53.10	51.25	1.0
	PC + GPB	81.0	79.5	81.0	70.0	20.5	38.1	50.75	54.05	1.0
	PP + GPB	81.0	74.8	81.0	71.0	25.2	25.3	53.10	48.15	.66

Appendix

Table 13: Belief injection and debate in open-source models. PC: persona capping; PP: persona prompting.

p

: cluster-level sign-flip permutation test on average accuracy with claims as clusters, Holm-adjusted across the 18 tests in the table.

			Accuracy (%)			Debate rev. (%)		Delib. rev. (%)		Confidence
Configuration	Panels	$n$	Pre	Debate	Delib.	T $\rightarrow$ F	F $\rightarrow$ T	T $\rightarrow$ F	F $\rightarrow$ T	Pre	Debate	Delib.
Deliberation, non-diverse
3 judges + consensus a	G-maj	188	88.83	92.55	81.91	3.72	7.45	10.64	0.00	84.96	80.39	–
	E-maj	198	14.65	7.58	8.08	13.64	6.57	2.02	2.53	83.86	79.58	–
	All	386	50.78	48.96	44.04	8.81	6.99	6.22	1.30	84.39	79.97	–
3 judges	G-maj	594	64.31	66.84	68.69	4.21	6.73	4.21	6.06	84.92	80.50	81.51

Appendix

Table 14: All multi-judge configurations (Claude Sonnet 4 with the GPB system prompt in non-diverse conditions). G-maj/E-maj: groups with a grounded or erroneous majority. Debate: post-debate; Delib.: post-deliberation. Reversals are percentages of

n

. a Accuracy and reversals refer to the group decision and

n

counts panels; confidence is the mean across judges and is not elicited after consensus deliberation.

Test	$p$	$p_{\text{Holm}}$
Insight 8: best protocol (3 judges, non-diverse)
V: pre $\rightarrow$ debate	.257	1.0
WV: pre $\rightarrow$ debate	.350	1.0
D: pre $\rightarrow$ delib.	.679	1.0
D+C: pre $\rightarrow$ debate	.571	1.0
D+C: debate $\rightarrow$ delib.	.003	.022

Appendix

Table 15: Hypothesis tests for multi-judge protocols, grouped by Holm-Bonferroni family, with debates as clusters. V: voting; WV: weighted voting; D: deliberation; D+C: deliberation with consensus; Div: diverse deliberation; G/E: grounded/erroneous. Within-protocol changes use cluster-level McNemar’s tests; between-protocol comparisons use cluster-level paired permutation tests, matching panels built from the same debate, majority composition, and presentation order. Insight 11 comparisons between groups use logistic (switching) and linear (confidence) regressions with debate-clustered standard errors. b Changes in accuracy of grounded and erroneous judges across the five configurations; ranges are reported.

Figure 10: Hybrid deliberation (one human and two LLM judges per room). (a) Accuracy and (b) mean confidence at each stage for grounded (blue) and erroneous (red) judges; solid lines denote human judges and dashed lines LLM judges. Error bars are 95% bootstrap confidence intervals, resampling participants for humans and debates for LLM judges.

Multi-Agent Debate

Multi-Agent Debate studies how language-model agents exchange arguments, critique answers, and combine judgments for collective reasoning.

See all 142 papers

AI Safety via Debate is Compromised by Cognitive Biases
Oct 4, 2026Gefei Liu, Sonya Rashkovan, Sophia Lloyd George +2Cognitive Bias in Language Models Language Model Safety Evaluation
Brown University
Knowledge Divergence and the Value of Debate for Scalable Oversight
Mar 5, 2026Robin YoungMulti-Agent Debate Scalable Oversight
Department of Computer Science and Technology, University of Cambridge, Cambridge, UK
Collaborative Disagreement Resolution for Scalable Oversight
Jun 2, 2026Yuyang Jiang, Chacha Chen, Teng Wu +4Scalable Oversight Multi-Agent Debate
Department of Computer Science, University of Chicago, Chicago, IL, USA · Microsoft, Redmond, WA, USA · Department of Biostatistics and Bioinformatics, Duke University, Durham, NC, USA +1

Oct 4, 2026J/K move · Enter open · S save

AI Safety via Debate is Compromised by Cognitive Biases

Gefei Liu, Sonya Rashkovan, Sophia Lloyd George, Isaac Sheidlower+1

Brown University

Cognitive Bias in Language Models Language Model Safety Evaluation AI Safety

Open paper AskPDF arXiv

Reinforcement learning from human feedback (RLHF) has played a central role in making large language models responsive to human instructions. However, human evaluators often favor flattering or persuasive responses over truthful ones, creating incentives for models to appeal to evaluators at the expense of accuracy. AI safety via debate has been proposed as a way to improve the supervision of language models: in this paradigm, two agents argue opposing positions and challenge each other's claims, potentially exposing falsehoods to the adjudicator. A central premise of AI safety via debate is that truthful arguments are easier to defend than false ones under adversarial scrutiny. In this work, we investigate whether this advantage persists when debaters use rhetorical strategies that exploit biases in human judgment. Inspired by competitive debate, we construct 68 LLM-generated dialogues about detective mysteries with known culprits, spanning four interventions: anchoring, fallacy oversight, pro-jargon, and verbosity. We apply each intervention to either the side advocating for the true culprit or the side advocating for an innocent suspect, allowing us to distinguish influence on adjudication from correctness. In a study with 369 participants, we find that, pooled across bias types, these interventions significantly shift judgments toward the manipulated side. These findings expose a vulnerability in debate-based supervision: human adjudication is sensitive to manipulative rhetorical strategies.

Abstract

Multi-Agent Debate

Explore similar work

AI Safety via Debate is Compromised by Cognitive Biases

Knowledge Divergence and the Value of Debate for Scalable Oversight

Collaborative Disagreement Resolution for Scalable Oversight