Retrieval-augmented generation (RAG) effectively addresses issues of static knowledge and hallucination in large language models. Existing studies mostly focus on question scenarios with clear user intents and concise answers. However, it is prevalent that users issue broad, open-ended queries with diverse sub-intents, for which they desire rich and long-form answers covering multiple relevant aspects. To tackle this important yet underexplored problem, we propose a novel RAG framework, namely RichRAG. It includes a sub-aspect explorer to identify potential sub-aspects of input questions, a multi-faceted retriever to build a candidate pool of diverse external documents related to these sub-aspects, and a generative list-wise ranker, which is a key module to provide the top-k most valuable documents for the final generator. These ranked documents sufficiently cover various query aspects and are aware of the generator's preferences, hence incentivizing it to produce rich and comprehensive responses for users. The training of our ranker involves a supervised fine-tuning stage to ensure the basic coverage of documents, and a reinforcement learning stage to align downstream LLM's preferences to the ranking of documents. Experimental results on two publicly available datasets prove that our framework effectively and efficiently provides comprehensive and satisfying responses to users.

翻译：检索增强生成（RAG）有效解决了大语言模型中静态知识与幻觉问题。现有研究大多聚焦于用户意图明确且答案简洁的提问场景。然而，用户经常提出宽泛、开放式的查询，这些查询包含多样的子意图，用户期望获得涵盖多个相关方面的丰富且长篇的回答。为应对这一重要但尚未充分探索的问题，我们提出了一种新颖的RAG框架，即RichRAG。它包括一个子方面探索器，用于识别输入问题的潜在子方面；一个多面性检索器，用于构建与这些子方面相关的多样化外部文档候选池；以及一个生成式列表排序器，该排序器作为关键模块，为最终生成器提供最具价值的top-k文档。这些排序后的文档充分覆盖了查询的各个方面，并考虑了生成器的偏好，从而激励其为用户生成丰富而全面的回答。我们排序器的训练包含一个监督微调阶段以确保文档的基本覆盖，以及一个强化学习阶段以使下游大语言模型的偏好与文档排序对齐。在两个公开数据集上的实验结果证明，我们的框架能有效且高效地为用户提供全面且令人满意的回答。