Conversational multi-doc question answering aims to answer specific questions based on the retrieved documents as well as the contextual conversations. In this paper, we introduce our winning approach for the "Conversational Multi-Doc QA" challenge in WSDM Cup 2024, which exploits the superior natural language understanding and generation capability of Large Language Models (LLMs). We first adapt LLMs to the task, then devise a hybrid training strategy to make the most of in-domain unlabeled data. Moreover, an advanced text embedding model is adopted to filter out potentially irrelevant documents and several approaches are designed and compared for the model ensemble. Equipped with all these techniques, our solution finally ranked 1st place in WSDM Cup 2024, surpassing its rivals to a large extent. The source codes have been released at https://github.com/zhangzhao219/WSDM-Cup-2024.

翻译：对话式多文档问答旨在基于检索到的文档以及上下文对话来回答特定问题。本文介绍了我们在WSDM Cup 2024“对话式多文档问答”挑战赛中获胜的方法，该方法充分利用了大语言模型（LLMs）卓越的自然语言理解和生成能力。我们首先将大语言模型适配到该任务上，随后设计了一种混合训练策略以充分利用域内未标注数据。此外，我们采用先进的文本嵌入模型来过滤掉潜在不相关文档，并设计并比较了多种模型集成方法。凭借这些技术，我们的解决方案最终在WSDM Cup 2024中夺得第一名，大幅领先竞争对手。源代码已发布在 https://github.com/zhangzhao219/WSDM-Cup-2024。