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

2026-02-27

AI Summary

This work addresses the limited interpretability and lack of user intervention capabilities of large language models (LLMs) in binary decision tasks by proposing and implementing an interactive visualization system based on Argumentative Large Language Models (ArgLLM). The system enables LLMs to generate structured reasoning processes, provides intuitive visual explanations, and allows users to actively interrogate and correct reasoning errors in real time. Furthermore, it integrates trusted external knowledge sources to strengthen the evidential basis of decisions. As the first interactive platform supporting human–AI collaborative argumentation within the ArgLLM framework, the publicly released system ArgLLM-App (https://argllm.app) demonstrates its effectiveness in enhancing decision transparency, model interpretability, and meaningful user participation.

Technology Category

• Knowledge Representation and Reasoning: Argumentation
• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Agreement, Argumentation & Negotiation

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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.

Problem

• Argumentative Reasoning
• Explainability
• Contestability
• Large Language Models
• Human-AI Interaction

Innovation

• Argumentative LLMs
• Explainable AI
• Interactive Reasoning
• Modular Architecture
• Human-AI Collaboration