arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2405.13015cs.CLcs.AI
收藏

基于大语言模型的辅助辩论构建器

Assisted Debate Builder with Large Language Models

Univ Lyon, UCBL(里昂大学,克洛德·贝尔纳里昂第一大学);CNRS(法国国家科学研究中心);INSA Lyon(里昂国立应用科学学院);LIRIS(里昂信息科学与系统实验室)

Elliot Faugier, Frédéric Armetta, Angela Bonifati, Bruno Yun

AI总结:

我们提出ADBL2,一个基于大语言模型的开源辅助辩论构建工具,支持关系验证与论证生成,并提供微调Mistral-7B模型,F1达90.59%。

摘要:

我们介绍了ADBL2,一个辅助辩论构建工具。它基于大语言模型在广泛领域中进行泛化和基于关系的论证挖掘的能力。它是第一个利用基于关系的挖掘来(1)验证辩论中预先建立的关系,以及(2)通过大语言模型辅助创建新论证的开源工具。ADBL2高度模块化,可以与任何作为插件使用的开源大语言模型配合工作。作为副产品,我们还提供了第一个针对基于关系的论证挖掘进行微调的Mistral-7B大语言模型,可供ADBL2使用,该模型在所有领域中的整体F1分数达到90.59%,优于现有方法。

英文摘要:

We introduce ADBL2, an assisted debate builder tool. It is based on the capability of large language models to generalise and perform relation-based argument mining in a wide-variety of domains. It is the first open-source tool that leverages relation-based mining for (1) the verification of pre-established relations in a debate and (2) the assisted creation of new arguments by means of large language models. ADBL2 is highly modular and can work with any open-source large language models that are used as plugins. As a by-product, we also provide the first fine-tuned Mistral-7B large language model for relation-based argument mining, usable by ADBL2, which outperforms existing approaches for this task with an overall F1-score of 90.59% across all domains.

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。

↑