Chain-of-Discussion: A Multi-Model Framework for Complex Evidence-Based Question Answering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tao, Mingxu, Zhao, Dongyan, Feng, Yansong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929631314051072
author Tao, Mingxu
Zhao, Dongyan
Feng, Yansong
author_facet Tao, Mingxu
Zhao, Dongyan
Feng, Yansong
contents Open-ended question answering requires models to find appropriate evidence to form wellreasoned, comprehensive and helpful answers. In practical applications, models also need to engage in extended discussions on potential scenarios closely relevant to the question. With augmentation of retrieval module, open-source Large Language Models (LLMs) can produce coherent answers often with different focuses, but are still sub-optimal in terms of reliable evidence selection and in-depth question analysis. In this paper, we propose a novel Chain-ofDiscussion framework to leverage the synergy among multiple open-source LLMs aiming to provide more correct and more comprehensive answers for open-ended QA, although they are not strong enough individually. Our experiments show that discussions among multiple LLMs play a vital role in enhancing the quality of answers.
format Preprint
id arxiv_https___arxiv_org_abs_2402_16313
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Chain-of-Discussion: A Multi-Model Framework for Complex Evidence-Based Question Answering
Tao, Mingxu
Zhao, Dongyan
Feng, Yansong
Computation and Language
Artificial Intelligence
Open-ended question answering requires models to find appropriate evidence to form wellreasoned, comprehensive and helpful answers. In practical applications, models also need to engage in extended discussions on potential scenarios closely relevant to the question. With augmentation of retrieval module, open-source Large Language Models (LLMs) can produce coherent answers often with different focuses, but are still sub-optimal in terms of reliable evidence selection and in-depth question analysis. In this paper, we propose a novel Chain-ofDiscussion framework to leverage the synergy among multiple open-source LLMs aiming to provide more correct and more comprehensive answers for open-ended QA, although they are not strong enough individually. Our experiments show that discussions among multiple LLMs play a vital role in enhancing the quality of answers.
title Chain-of-Discussion: A Multi-Model Framework for Complex Evidence-Based Question Answering
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2402.16313