# Interpreting and Mitigating Hallucination in MLLMs through Multi-agent Debate

arXiv: https://arxiv.org/abs/2407.20505 · HTML: https://mlsanity.com/paper/2407.20505/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 23 of its 28 references that are in the map.
- First posted on arXiv 30 Jul 2024.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 23 of 23)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [Aligning Large Multimodal Models with Factually Augmented RLHF](https://mlsanity.com/paper/2309.14525/) (2023)
- [A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge](https://mlsanity.com/paper/2206.01718/) (2022)
- [Benchmarking Large Language Models for News Summarization](https://mlsanity.com/paper/2301.13848/) (2023)
- [Hallucination of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2404.18930/) (2024)
- [Detecting and Preventing Hallucinations in Large Vision Language Models](https://mlsanity.com/paper/2308.06394/) (2023)
- [Reasoning with Language Model Prompting: A Survey](https://mlsanity.com/paper/2212.09597/) (2022)
- [Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future](https://mlsanity.com/paper/2309.15402/) (2023)
- [HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data](https://mlsanity.com/paper/2311.13614/) (2023)
- [A Survey on Large Language Model Hallucination via a Creativity Perspective](https://mlsanity.com/paper/2402.06647/) (2024)
- [Assessing and Understanding Creativity in Large Language Models](https://mlsanity.com/paper/2401.12491/) (2024)
- [Hal-Eval: A Universal and Fine-grained Hallucination Evaluation Framework for Large Vision Language Models](https://mlsanity.com/paper/2402.15721/) (2024)

## Built on by (most cited first, 16 of 16)

- [Can LLM Agents Really Debate? A Controlled Study of Multi-Agent Debate in Logical Reasoning](https://mlsanity.com/paper/2511.07784/) (2025)
- [Creativity in LLM-based Multi-Agent Systems: A Survey](https://mlsanity.com/paper/2505.21116/) (2025)
- [Mirage in the Eyes: Hallucination Attack on Multi-modal Large Language Models with Only Attention Sink](https://mlsanity.com/paper/2501.15269/) (2025)
- [Enhancing Financial Question Answering with a Multi-Agent Reflection Framework](https://mlsanity.com/paper/2410.21741/) (2024)
- [Hallucination Mitigation using Agentic AI Natural Language-Based Frameworks](https://mlsanity.com/paper/2501.13946/) (2025)
- [Defending LVLMs Against Vision Attacks through Partial-Perception Supervision](https://mlsanity.com/paper/2412.12722/) (2024)
- [CCHall: A Novel Benchmark for Joint Cross-Lingual and Cross-Modal Hallucinations Detection in Large Language Models](https://mlsanity.com/paper/2505.19108/) (2025)
- [ContextCov: Deriving and Enforcing Executable Constraints from Agent Instruction Files](https://mlsanity.com/paper/2603.00822/) (2026)
- [PhishDebate: An LLM-Based Multi-Agent Framework for Phishing Website Detection](https://mlsanity.com/paper/2506.15656/) (2025)
- [Distributional Semantics Tracing: A Framework for Explaining Hallucinations in Large Language Models](https://mlsanity.com/paper/2510.06107/) (2025)
- [Empowering Multimodal LLMs with External Tools: A Comprehensive Survey](https://mlsanity.com/paper/2508.10955/) (2025)
- [Cross-Modal Memory Compression for Efficient Multi-Agent Debate](https://mlsanity.com/paper/2602.00454/) (2026)
- [An Evolutionary Large Language Model for Hallucination Mitigation](https://mlsanity.com/paper/2412.02790/) (2024)
- [A Low-Rank Method for Vision Language Model Hallucination Mitigation in Autonomous Driving](https://mlsanity.com/paper/2511.06496/) (2025)
- [The Inverse-Wisdom Law: Architectural Tribalism and the Consensus Paradox in Agentic Swarms](https://mlsanity.com/paper/2604.27274/) (2026)
- [Social Reasoning in Machines: Investigating Collective Truth-Seeking Dynamics in Large Language Model Debate](https://mlsanity.com/paper/2605.30391/) (2026)

## Abstract (arXiv)

MLLMs often generate outputs that are inconsistent with the visual content, a challenge known as hallucination. Previous methods focus on determining whether a generated output is hallucinated, without identifying which image region leads to the hallucination or interpreting why such hallucinations occur. In this paper, we argue that hallucination in MLLMs is partially due to a lack of slow-thinking and divergent-thinking in these models. To address this, we propose adopting a self-reflection scheme to promote slow-thinking. Furthermore, we consider eliminating hallucination as a complex reasoning task and propose a multi-agent debate approach to encourage divergent-thinking. Consequently, our approach can not only mitigate hallucinations but also interpret why they occur and detail the specifics of hallucination. In addition, we propose to distinguish creativity from hallucination in the context of MLLMs, and illustrate how to evaluate MLLMs' creativity capability. Extensive experiments on various benchmarks demonstrate that our approach exhibits generalized hallucinations-mitigating performance across several MLLMs.