ArgLLM-App: An Interactive System for Argumentative Reasoning with Large Language Models
This work addresses the need for explainable and contestable AI decisions in human-AI interaction, though it is incremental as it builds on existing ArgLLM approaches.
The authors tackled the problem of making AI decision-making more transparent and contestable by developing ArgLLM-App, a web-based system that implements argumentative LLMs for binary tasks, resulting in a publicly available tool with interactive visualizations and modular integration of external sources.
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.