超越单一模型：通过辩论增强 LLM 对请求中歧义的检测
Beyond Single Models: Enhancing LLM Detection of Ambiguity in Requests through Debate
AI总结：
本文提出多智能体辩论框架，利用三种 LLM 架构和含多种歧义的数据集，显著提升模型对用户请求中歧义的检测与解决能力，为构建更稳健的语言理解系统提供新见解。
摘要：
大型语言模型（LLMs）在理解和生成人类语言方面展现出显著能力，有助于与复杂系统进行更自然的交互。然而，它们在处理由 LLMs 处理的用户请求中的歧义时面临挑战。为了解决这些挑战，本文引入并评估了一个多智能体辩论框架，旨在增强超越单一模型的检测和解决能力。该框架包含三种 LLM 架构（Llama3-8B、Gemma2-9B 和 Mistral-7B 变体）以及一个包含多种歧义的数据集。辩论框架显著提升了 Llama3-8B 和 Mistral-7B 变体相对于其各自基线的性能，其中以 Mistral-7B 为主导的辩论取得了 76.7% 的显著成功率，并证明在处理复杂歧义和达成高效共识方面尤为有效。尽管不同模型对协作策略的响应存在差异，这些发现仍凸显了辩论框架作为增强 LLM 能力的针对性方法的价值。这项工作通过展示结构化辩论如何提升交互系统中的清晰度，为开发更稳健和自适应的语言理解系统提供了重要见解。
英文摘要：
Large Language Models (LLMs) have demonstrated significant capabilities in understanding and generating human language, contributing to more natural interactions with complex systems. However, they face challenges such as ambiguity in user requests processed by LLMs. To address these challenges, this paper introduces and evaluates a multi-agent debate framework designed to enhance detection and resolution capabilities beyond single models. The framework consists of three LLM architectures (Llama3-8B, Gemma2-9B, and Mistral-7B variants) and a dataset with diverse ambiguities. The debate framework markedly enhanced the performance of Llama3-8B and Mistral-7B variants over their individual baselines, with Mistral-7B-led debates achieving a notable 76.7% success rate and proving particularly effective for complex ambiguities and efficient consensus. While acknowledging varying model responses to collaborative strategies, these findings underscore the debate framework's value as a targeted method for augmenting LLM capabilities. This work offers important insights for developing more robust and adaptive language understanding systems by showing how structured debates can lead to improved clarity in interactive systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
