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

TL;DR

ArgLLM-App is an interactive web-based system that uses large language models for argumentative reasoning, providing explanations and contestability features to improve decision-making transparency and user engagement.

Contribution

The paper introduces a modular, interactive web system for argumentative reasoning with LLMs, supporting visualization, external sources, and user contestation.

Findings

System enables visual explanations of LLM reasoning.

Supports interaction and contestation by users.

Publicly available with demonstration resources.

Abstract

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.