mlsanityData to 14 Oct 2026

Debating Truth: Debate-driven Claim Verification with Multiple Large Language Model Agents

arXiv 2507.19090 ↗First posted 25 Jul 2025cs.CLcited by 6

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

State-of-the-art single-agent claim verification methods struggle with complex claims that require nuanced analysis of multifaceted evidence. Inspired by real-world professional fact-checkers, we propose DebateCV, the first debate-driven claim verification framework powered by multiple LLM agents. In DebateCV, two textitDebaters argue opposing stances to surface subtle errors in single-agent assessments. A decisive textitModerator is then required to weigh the evidential strength of conflicting arguments to deliver an accurate verdict. Yet, zero-shot Moderators are biased toward neutral judgments, and no datasets exist for training them. To bridge this gap, we propose Debate-SFT, a post-training framework that leverages synthetic data to enhance agents' ability to effectively adjudicate debates for claim verification. Results show that our methods surpass state-of-the-art non-debate approaches in both accuracy (across various evidence conditions) and justification quality.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 37 of its 65 references that are in the map. First posted on arXiv 25 Jul 2025.

Builds on

37 of 65 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Stance Detection with Collaborative Role-Infused LLM-Based Agents16 Oct
  2. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View3 Oct
  3. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate30 May

Other references · 34

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  4. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  5. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  6. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  7. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  8. 2025LLMs Get Lost In Multi-Turn Conversationcited by 429
  9. 2021A Survey on Automated Fact-Checkingcited by 378
  10. 2024Debating with More Persuasive LLMs Leads to More Truthful Answerscited by 266
  11. 2023AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Webcited by 144
  12. 2023Complex Claim Verification with Evidence Retrieved in the Wildcited by 110
22 more
  1. 2018Towards Automated Factchecking: Developing an Annotation Schema and Benchmark for Consistent Automated Claim Detectioncited by 55
  2. 2024Explainable Fake News Detection With Large Language Model via Defense Among Competing Wisdomcited by 50
  3. 2024Can LLMs Produce Faithful Explanations For Fact-checking? Towards Faithful Explainable Fact-Checking via Multi-Agent Debatecited by 48
  4. 2024DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Expertscited by 43
  5. 2024Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statementscited by 34
  6. 2024The Automated Verification of Textual Claims (AVeriTeC) Shared Taskcited by 29
  7. 2025Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checkingcited by 29
  8. 2025The Truth Becomes Clearer Through Debate! Multi-Agent Systems with Large Language Models Unmask Fake Newscited by 29
  9. 2025Removal of Hallucination on Hallucination: Debate-Augmented RAGcited by 29
  10. 2024Retrieval Augmented Fact Verification by Synthesizing Contrastive Argumentscited by 25
  11. 2025FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language Modelscited by 19
  12. 2024Let Silence Speak: Enhancing Fake News Detection with Generated Comments from Large Language Modelscited by 17
  13. 2022Improved Target-specific Stance Detection on Social Media Platforms by Delving into Conversation Threadscited by 16
  14. 2025Resolving Conflicting Evidence in Automated Fact-Checking: A Study on Retrieval-Augmented LLMscited by 16
  15. 2024MCFEND: A Multi-source Benchmark Dataset for Chinese Fake News Detectioncited by 12
  16. 2024HerO at AVeriTeC: The Herd of Open Large Language Models for Verifying Real-World Claimscited by 12
  17. 2025Debate-to-Detect: Reformulating Misinformation Detection as a Real-World Debate with Large Language Modelscited by 12
  18. 2024AIC CTU system at AVeriTeC: Re-framing automated fact-checking as a simple RAG taskcited by 8
  19. 2022"This is Fake News": Characterizing the Spontaneous Debunking from Twitter Users to COVID-19 False Informationcited by 5
  20. 2024Search, Examine and Early-Termination: Fake News Detection with Annotation-Free Evidencescited by 3
  21. 2024Take It Easy: Label-Adaptive Self-Rationalization for Fact Verification and Explanation Generationcited by 3
  22. 2025From Generation to Detection: A Multimodal Multi-Task Dataset for Benchmarking Health Misinformationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 3.

6 papers.

  1. 2025Can LLM Agents Really Debate? A Controlled Study of Multi-Agent Debate in Logical Reasoningcited by 29
  2. 2025Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking Systemcited by 4
  3. 2025Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanismcited by 4
  4. 2026Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verificationcited by 4
  5. 2026From Verdict to Process: Agentic Reinforcement Learning for Multi-Stage Fact Verificationcited by 1
  6. 2026The impact of multi-agent debate protocols on debate quality: a controlled case studycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Tool-MAD: A Multi-Agent Debate Framework for Fact Verification with Diverse Tool Augmentation and Adaptive Retrieval
  2. 2026A Theory of Post-hoc Debate Judgement
  3. 2026Towards Mitigating Fabricated Consensus: The Active Provenance Gate for Multi-Agent Debate Synthesis
  4. 2026MABPD: Multi-Agent Bias Probing & Detection via Structured Argument Debate
  5. 2026Demystifying Multi-Agent Debate: The Role of Confidence and Diversity
  6. 2026CLAIR-Fin: An Adversarial Multi-Agent Framework for Claim-Level Verification and Adaptive Debate in Cross-Modal Financial QA
  7. 2026Mixture of Debaters: Learn to Debate at Architectural Level in Multi-Agent Reasoning
  8. 2026Multimodal Collaborative Debate for Zero-Shot Time Series Reasoning