IntelliProof: An Argumentation Network-based Conversational Helper for Organized Reflection

2025-11-06

AI Summary

Existing automated essay scoring systems neglect user experience and fail to reveal the argumentative structure and quality of persuasive essays. Method: We propose an interactive assessment system grounded in argumentation networks: leveraging large language models (LLMs) to automatically identify claim nodes and support/attack relations, constructing interpretable, structured argument graphs; integrating human-in-the-loop fine-tuning of relation classification to ensure logical validity; and enabling dynamic exploration, natural-language question-answering, and coherence quantification via an interactive visualization interface. Contribution/Results: This work pioneers the tight integration of LLM-based reasoning, human verification, and interactive visualization—bridging the gap between textual semantic structure and user cognition. The system significantly improves argument parsing efficiency, assessment transparency, and user comprehension depth. It is open-sourced and accompanied by a public demo.

Technology Category

• Knowledge Representation and Reasoning: Argumentation
• Natural Language Processing: Discourse, Pragmatics & Argument Mining
• Multiagent Systems: Agreement, Argumentation & Negotiation

Application Category

• 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
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

We present IntelliProof, an interactive system for analyzing argumentative essays through LLMs. IntelliProof structures an essay as an argumentation graph, where claims are represented as nodes, supporting evidence is attached as node properties, and edges encode supporting or attacking relations. Unlike existing automated essay scoring systems, IntelliProof emphasizes the user experience: each relation is initially classified and scored by an LLM, then visualized for enhanced understanding. The system provides justifications for classifications and produces quantitative measures for essay coherence. It enables rapid exploration of argumentative quality while retaining human oversight. In addition, IntelliProof provides a set of tools for a better understanding of an argumentative essay and its corresponding graph in natural language, bridging the gap between the structural semantics of argumentative essays and the user's understanding of a given text. A live demo and the system are available here to try: extbf{https://intelliproof.vercel.app}

Problem

• Analyzing argumentative essays using LLMs and argumentation graphs
• Providing visualizations and justifications for argument relations
• Bridging structural semantics with user understanding of essays

Innovation

• Uses LLMs to analyze argumentative essays
• Structures essays as argumentation graphs with relations
• Provides visualizations and justifications for classifications