Multi-party chat often contains interleaved dialogues because multiple participants can discuss different topics at the same time. Dialogue disentanglement addresses this problem by separating an entangled utterance sequence into coherent dialogues. While large language models (LLMs) are promising for this task, they still struggle with dialogue disentanglement and achieve low accuracy. This paper proposes an automatic prompt optimization for LLM based dialogue disentanglement. We decompose the prompt into three components: task instruction, utterance representation, and output instruction, and optimize them using GEPA, an optimization method for compound AI systems. Experiments on benchmark datasets show that the optimized prompts improve dialogue disentanglement accuracy over the original prompts and can surpass hand crafted prompts.

翻译：多方聊天中常包含交织的对话，因为多个参与者可同时讨论不同主题。对话解缠通过将纠缠的话语序列分离为连贯对话来解决该问题。尽管大语言模型在此任务中展现出潜力，但其在对话解缠方面仍存在困难且准确率较低。本文提出一种面向大语言模型的自动提示优化方法用于对话解缠。我们将提示分解为三个组件：任务指令、话语表征和输出指令，并采用面向复合AI系统的优化方法GEPA对其进行优化。基准数据集实验表明，优化后的提示相较于原始提示能提升对话解缠准确率，且可超越人工设计的提示。