让大模型辩论更透明，用户可实时质疑推理过程
ArgLLM-App: An Interactive System for Argumentative Reasoning with Large Language Models
- 构建交互式网页系统，用大模型生成可解释的二元决策
- 支持可视化推理链，允许用户发现并挑战错误推理
- 模块化设计，可接入可信外部数据源，适合审慎决策场景
论辩型大语言模型（ArgLLM）通过结合大语言模型与计算论辩技术，旨在实现可解释且可被人类质疑的决策。本文提出一个基于Web的交互系统ArgLLM-App，用于执行二元任务。该系统支持生成推理过程的可视化展示，并允许用户与系统互动，识别并挑战其中的错误推理。系统高度模块化，可集成可信外部信息源。ArgLLM-App已公开发布于https://argllm.app，视频演示见https://youtu.be/vzwlGOr0sPM。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。