讨论链：一种面向复杂基于证据问答的多模型框架
Chain-of-Discussion: A Multi-Model Framework for Complex Evidence-Based Question Answering
AI总结：
提出讨论链框架，利用多个开源大模型的协同讨论，提升开放式基于证据问答中证据选择与答案的全面性和正确性。
摘要：
开放式问答要求模型找到合适的证据，以形成推理充分、全面且有帮助的答案。在实际应用中，模型还需要就与问题密切相关的潜在场景进行扩展讨论。通过检索模块的增强，开源大型语言模型（LLMs）能够生成连贯的答案，但往往侧重点不同，在可靠的证据选择和深入的问题分析方面仍非最优。在本文中，我们提出了一种新颖的讨论链（Chain-of-Discussion）框架，利用多个开源LLM之间的协同作用，旨在为开放式问答提供更正确、更全面的答案，尽管它们单独而言不够强大。我们的实验表明，多个LLM之间的讨论在提升答案质量方面发挥着至关重要的作用。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
