arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.24172cs.CLcs.AI
收藏

ArgLLM-App:基于大语言模型的论证推理交互系统

ArgLLM-App: An Interactive System for Argumentative Reasoning with Large Language Models

Imperial College London(伦敦帝国学院)

Adam Dejl, Deniz Gorur, Francesca Toni

AI总结:

ArgLLM-App是一个基于大语言模型的论证推理交互系统,通过可视化解释和用户交互实现决策的可解释性和可挑战性。

摘要:

论证大语言模型(ArgLLMs)是一种利用大语言模型(LLMs)和计算论证进行决策的现有方法,旨在使最终决策能够忠实解释并可被人类挑战。本文提出了一种基于网页的系统,实现ArgLLM赋能的代理,用于二元任务。ArgLLM-App支持可视化生成的解释并与人类用户交互,允许用户识别和挑战系统推理中的任何错误。它高度模块化,能够从可信的外部来源获取信息。ArgLLM-App在https://argllm.app公开可用,演示视频在https://youtu.be/vzwlGOr0sPM。

英文摘要:

Argumentative LLMs (ArgLLMs) are an existing approach leveraging Large Language Models (LLMs) and computational argumentation for decision-making, with the aim of making the resulting decisions faithfully explainable to and contestable by humans. Here we propose a web-based system implementing ArgLLM-empowered agents for binary tasks. ArgLLM-App supports visualisation of the produced explanations and interaction with human users, allowing them to identify and contest any mistakes in the system's reasoning. It is highly modular and enables drawing information from trusted external sources. ArgLLM-App is publicly available at https://argllm.app, with a video demonstration at https://youtu.be/vzwlGOr0sPM.

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。

↑