用第三方大模型优化多智能体共识，降低幻觉风险。
Enhancing Multi-Agent Consensus through Third-Party LLM Integration: Analyzing Uncertainty and Mitigating Hallucinations in Large Language Models
- 引入第三方LLM通过不确定性分析动态调整注意力权重。
- 在算术数据集上超越传统多智能体基线，共识准确率提升显著。
- 适合研究大模型幻觉缓解与多智能体协作的学者参考。
大型语言模型（LLMs）在处理复杂推理任务时仍面临幻觉问题，限制了其实际应用。本文提出一种新方法，通过集成不同LLM以扩展知识边界、降低对单一模型的依赖，并促进智能体间的深度讨论。主要贡献包括：1）引入第三方LLM，基于不确定性估计与置信度分析调节智能体的注意力权重，优化多智能体系统中的共识形成；2）在算术数据集上的实验验证了该方法的有效性，性能优于传统多智能体基线。该研究为大模型在复杂任务中缓解幻觉现象提供了新思路。
原文摘要 · Abstract (English)
Large Language Models (LLMs) still face challenges when dealing with complex reasoning tasks, often resulting in hallucinations, which limit the practical application of LLMs. To alleviate this issue, this paper proposes a new method that integrates different LLMs to expand the knowledge boundary, reduce dependence on a single model, and promote in-depth debate among agents. The main contributions include: 1) Introducing third-party LLMs to adjust the attention weights of agents through uncertainty estimation and confidence analysis, optimizing consensus formation in multi-agent systems; 2) Experiments on arithmetic datasets have validated the effectiveness of the method, surpassing traditional multi-agent baselines. This research provides a new perspective for large models to alleviate hallucination phenomena when dealing with complex tasks.
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。