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

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 weproposeaweb-basedsystemimplementingArgLLM-empowered agents for binary tasks. ArgLLM-App supports visualisation of the produced explanations and interaction with human users, allowing themtoidentifyandcontestanymistakesinthesystem’sreasoning. It is highly modular and enables drawing information from trusted external sources. ArgLLM-App is publicly available at argllm. app, with a video demonstration at youtu. be/vzwlGOr0sPM.

Authors

• Adam Dejl Imperial College London
• Deniz Gorur Imperial College London
• Francesca Toni Imperial College London

Keywords

• Argumentation
• LLMs
• RAG