Enhancing Multi-Agent Consensus through Third-Party LLM Integration: Analyzing Uncertainty and Mitigating Hallucinations in Large Language Models
It addresses hallucinations in LLMs for multi-agent systems, offering an incremental improvement in consensus formation.
This paper tackled the problem of hallucinations in Large Language Models (LLMs) during complex reasoning tasks by integrating third-party LLMs to enhance multi-agent consensus, resulting in improved performance over traditional baselines on arithmetic datasets.
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.