让大模型学会多人对话，提升真实场景的交流能力。
Multi-Party Supervised Fine-tuning of Language Models for Multi-Party Dialogue Generation
- 设计多角色微调框架MuPaS，直接适配多人对话数据
- 在多人对话中实现更准确的发言者预测与高质量回应
- 适合会议记录、虚拟演练等复杂对话应用
大语言模型通常仅针对二人对话进行微调，难以适应多人对话场景，限制了其在多人会议、讨论及日常交流中的应用。现有研究虽采用多智能体框架，但基础模型仍为成对微调。本文提出多角色微调框架MuPaS，基于多人对话数据集训练，证明该简单框架可高效、有效对齐多人对话风格。设计两种训练策略，使MuPaS可转化为多人对话模拟器。大量实验表明，MuPaS在多人回复生成、发言者预测准确率、人工与自动评估的语句质量上均达到当前最优水平，并能合理生成分布外场景、话题与角色描述。该框架打通了大模型训练与复杂多人应用之间的鸿沟，适用于对话生成、虚拟排练或元宇宙场景。
原文摘要 · Abstract (English)
Large Language Models (LLM) are usually fine-tuned to participate in dyadic or two-party dialogues, which can not adapt well to multi-party dialogues (MPD), which hinders their applications in such scenarios including multi-personal meetings, discussions and daily communication. Previous LLM-based researches mainly focus on the multi-agent framework, while their base LLMs are still pairwisely fine-tuned. In this work, we design a multi-party fine-tuning framework (MuPaS) for LLMs on the multi-party dialogue datasets, and prove such a straightforward framework can let the LLM align with the multi-party conversation style efficiently and effectively. We also design two training strategies which can convert MuPaS into the MPD simulator. Substantial experiments show that MuPaS can achieve state-of-the-art multi-party response, higher accuracy of the-next-speaker prediction, higher human and automatic evaluated utterance qualities, and can even generate reasonably with out-of-distribution scene, topic and role descriptions. The MuPaS framework bridges the LLM training with more complicated multi-party applications, such as conversation generation, virtual rehearsal or meta-universe.
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。