Multi-hop question answering is a knowledge-intensive complex problem. Large Language Models (LLMs) use their Chain of Thoughts (CoT) capability to reason complex problems step by step, and retrieval-augmentation can effectively alleviate factual errors caused by outdated and unknown knowledge in LLMs. Recent works have introduced retrieval-augmentation in the CoT reasoning to solve multi-hop question answering. However, these chain methods have the following problems: 1) Retrieved irrelevant paragraphs may mislead the reasoning; 2) An error in the chain structure may lead to a cascade of errors. In this paper, we propose a dynamic retrieval framework called Tree of Reviews (ToR), where the root node is the question, and the other nodes are paragraphs from retrieval, extending different reasoning paths from the root node to other nodes. Our framework dynamically decides to initiate a new search, reject, or accept based on the paragraphs on the reasoning paths. Compared to related work, we introduce a tree structure to handle each retrieved paragraph separately, alleviating the misleading effect of irrelevant paragraphs on the reasoning path; the diversity of reasoning path extension reduces the impact of a single reasoning error on the whole. We conducted experiments on three different multi-hop question answering datasets. The results show that compared to the baseline methods, ToR achieves state-of-the-art performance in both retrieval and response generation. In addition, we propose two tree-based search optimization strategies, pruning and effective expansion, to reduce time overhead and increase the diversity of path extension. We will release our code.

翻译：多跳问答是一种知识密集型复杂问题。大语言模型（LLMs）利用其思维链（CoT）能力逐步推理复杂问题，而检索增强可有效缓解LLMs因知识过时和未知导致的事实性错误。近期研究在CoT推理中引入检索增强以解决多跳问答。然而，这些链式方法存在以下问题：1）检索到的无关段落可能误导推理；2）链式结构中的单点错误可能引发级联错误。本文提出一种名为推理树（ToR）的动态检索框架，其中根节点为问题，其余节点为检索段落，从根节点向其他节点延伸出不同推理路径。该框架根据推理路径上的段落动态决策：启动新搜索、拒绝或接受。与现有工作相比，我们引入树状结构分别处理每个检索段落，减轻无关段落对推理路径的误导；推理路径的多样性扩展降低了单次推理错误对整体的影响。我们在三个不同多跳问答数据集上进行实验，结果表明，与基线方法相比，ToR在检索和答案生成两方面均达到最优性能。此外，我们提出两种基于树的搜索优化策略——剪枝与有效扩展，以降低时间开销并增强路径扩展的多样性。我们将公开代码。