基于对比说话人感知学习的LLM多方对话生成
Contrastive Speaker-Aware Learning for Multi-party Dialogue Generation with LLMs
AI总结：
本文提出SA-LLM，通过说话人感知对比学习无需关系标注即可建模多方对话中的说话人角色与上下文连贯性，在流畅性、连贯性和多样性上超越现有基线。
摘要：
多方对话生成由于多个说话人之间复杂的交互以及交织的对话线程而面临显著挑战。传统方法在捕捉这些复杂性方面往往存在不足，尤其是在依赖人工标注的对话关系时。本文提出了Speaker-Attentive LLM（SA-LLM），这是一种新颖的生成模型，利用预训练大语言模型（LLMs）和说话人感知的对比学习策略来应对这些挑战。SA-LLM结合了说话人属性输入编码和对比学习目标，以隐式地学习上下文连贯性和说话人角色，而无需显式的关系标注。在Ubuntu IRC和Movie Dialogues数据集上的大量实验表明，SA-LLM在自动评估和人工评估中均显著优于最先进的基线模型，在流畅性、连贯性、信息量和回复多样性方面取得了优越的性能。消融研究和详细的错误分析进一步验证了所提出的说话人注意力训练方法的有效性，突显了其在不同说话人角色和上下文长度下的鲁棒性。结果强调了SA-LLM作为一种强大且无需标注的高质量多方对话生成解决方案的潜力。
英文摘要：
Multi-party dialogue generation presents significant challenges due to the complex interplay of multiple speakers and interwoven conversational threads. Traditional approaches often fall short in capturing these complexities, particularly when relying on manually annotated dialogue relations. This paper introduces Speaker-Attentive LLM (SA-LLM), a novel generative model that leverages pre-trained Large Language Models (LLMs) and a speaker-aware contrastive learning strategy to address these challenges. SA-LLM incorporates a speaker-attributed input encoding and a contrastive learning objective to implicitly learn contextual coherence and speaker roles without explicit relation annotations. Extensive experiments on the Ubuntu IRC and Movie Dialogues datasets demonstrate that SA-LLM significantly outperforms state-of-the-art baselines in automatic and human evaluations, achieving superior performance in fluency, coherence, informativeness, and response diversity. Ablation studies and detailed error analyses further validate the effectiveness of the proposed speaker-attentive training approach, highlighting its robustness across different speaker roles and context lengths. The results underscore the potential of SA-LLM as a powerful and annotation-free solution for high-quality multi-party dialogue generation.
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。
