Tree of Reviews: A Tree-based Dynamic Iterative Retrieval Framework for Multi-hop Question Answering
Li Jiapeng, Liu Runze, Li Yabo, Zhou Tong, Li Mingling, Chen Xiang

TL;DR
This paper introduces Tree of Reviews (ToR), a tree-structured dynamic retrieval framework for multi-hop question answering that improves reasoning accuracy and reduces errors by handling retrieved paragraphs separately and diversifying reasoning paths.
Contribution
The paper proposes a novel tree-based retrieval framework for multi-hop QA, addressing issues of irrelevant information and cascading errors in previous chain-based methods.
Findings
Achieves state-of-the-art performance on three datasets.
Reduces reasoning errors through tree-structured retrieval.
Improves efficiency with pruning and expansion strategies.
Abstract
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to reason complex problems step by step, and retrieval-augmentation can effectively alleviate factual errors caused by outdated and unknown knowledge in LLMs.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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Advanced Text Analysis Techniques · Expert finding and Q&A systems
MethodsPruning
