通过自我反思与多智能体协作，有效减少大模型幻觉。
InEx: Hallucination Mitigation via Introspection and Cross-Modal Multi-Agent Collaboration
- 用熵估计判断不确定性，让模型先自我反思再决策。
- 多智能体协作验证并修正答案，提升结果可靠性。
- 无需训练，适合希望降低幻觉的AI应用开发者。
幻觉仍是大语言模型（LLM）中的关键挑战，阻碍了多模态大语言模型（MLLM）的可靠发展。现有方法常依赖人工干预或未能充分利用智能体自主缓解幻觉的能力。受人类真实世界决策方式启发：先通过内省推理减少不确定性形成初步判断，再通过多视角外部验证得出最终结论。为此，我们提出InEx——一种无需训练的多智能体框架，可自主缓解幻觉。InEx引入基于熵的不确定性估计进行内部内省推理，提升决策可靠性；随后通过编辑智能体与自省智能体之间的跨模态多智能体协作，迭代验证并优化输出，进一步增强可信度。大量实验表明，InEx在通用和幻觉基准上均持续优于现有方法，性能提升4%至27%，且具备强鲁棒性。
原文摘要 · Abstract (English)
Hallucination remains a critical challenge in large language models (LLMs), hindering the development of reliable multimodal LLMs (MLLMs). Existing solutions often rely on human intervention or underutilize the agent's ability to autonomously mitigate hallucination. To address these limitations, we draw inspiration from how humans make reliable decisions in the real world. They begin with introspective reasoning to reduce uncertainty and form an initial judgment, then rely on external verification from diverse perspectives to reach a final decision. Motivated by this cognitive paradigm, we propose InEx, a training-free, multi-agent framework designed to autonomously mitigate hallucination. InEx introduces internal introspective reasoning, guided by entropy-based uncertainty estimation, to improve the reliability of the decision agent's reasoning process. The agent first generates a response, which is then iteratively verified and refined through external cross-modal multi-agent collaboration with the editing agent and self-reflection agents, further enhancing reliability and mitigating hallucination. Extensive experiments show that InEx consistently outperforms existing methods, achieving 4%-27% gains on general and hallucination benchmarks, and demonstrating strong robustness.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。