Answering Questions by Meta-Reasoning over Multiple Chains of Thought

Ori Yoran, Tomer Wolfson, Ben Bogin, Uri Katz, Daniel Deutch, Jonathan Berant

Submission Type: Regular Long Paper

Submission Track: Question Answering

Keywords: Question Answering, Multi-hop Question Answering, Reasoning, Few-shot, Chain of Thought

TL;DR: This paper introduces Multi-Chain Reasoning (MCR), an approach which prompts large language models to meta-reason over multiple chains of thought rather than aggregate their answers; MCR outperforms strong baselines on 7 multi-hop QA datasets.

Abstract: Modern systems for multi-hop question answering (QA) typically break questions into a sequence of reasoning steps, termed chain-of-thought (CoT), before arriving at a final answer. Often, multiple chains are sampled and aggregated through a voting mechanism over the final answers, but the intermediate steps themselves are discarded. While such approaches improve performance, they do not consider the relations between intermediate steps across chains and do not provide a unified explanation for the predicted answer. We introduce Multi-Chain Reasoning (MCR), an approach which prompts large language models to meta-reason over multiple chains of thought, rather than aggregate their answers. MCR examines different reasoning chains, mixes information between them and selects the most relevant facts in generating an explanation and predicting the answer. MCR outperforms strong baselines on 7 multi-hop QA datasets. Moreover, our analysis reveals that MCR explanations exhibit high quality, enabling humans to verify its answers.

Submission Number: 1505