Answering Questions by Meta-Reasoning over Multiple Chains of Thought

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yoran, Ori, Wolfson, Tomer, Bogin, Ben, Katz, Uri, Deutch, Daniel, Berant, Jonathan
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910551115825152
author Yoran, Ori
Wolfson, Tomer
Bogin, Ben
Katz, Uri
Deutch, Daniel
Berant, Jonathan
author_facet Yoran, Ori
Wolfson, Tomer
Bogin, Ben
Katz, Uri
Deutch, Daniel
Berant, Jonathan
contents 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 aggregating 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.
format Preprint
id arxiv_https___arxiv_org_abs_2304_13007
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Answering Questions by Meta-Reasoning over Multiple Chains of Thought
Yoran, Ori
Wolfson, Tomer
Bogin, Ben
Katz, Uri
Deutch, Daniel
Berant, Jonathan
Computation and Language
Artificial Intelligence
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 aggregating 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.
title Answering Questions by Meta-Reasoning over Multiple Chains of Thought
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2304.13007