LLM-based Argument Mining meets Argumentation and Description Logics: a Unified Framework for Reasoning about Debates

TL;DR

This paper introduces a unified framework combining argument mining, quantitative reasoning, and description logics to enable transparent, explainable analysis of debates, addressing LLM limitations in structured reasoning.

Contribution

It integrates learning-based argument extraction with formal reasoning and ontology querying, creating a transparent system for debate analysis that surpasses purely statistical methods.

Findings

Extracts fuzzy argumentation knowledge bases from debates

Computes argument strengths using quantitative semantics

Enables expressive query answering via description logics

Abstract

Large Language Models (LLMs) achieve strong performance in analyzing and generating text, yet they struggle with explicit, transparent, and verifiable reasoning over complex texts such as those containing debates. In particular, they lack structured representations that capture how arguments support or attack each other and how their relative strengths determine overall acceptability. We encompass these limitations by proposing a framework that integrates learning-based argument mining with quantitative reasoning and ontology-based querying. Starting from a raw debate text, the framework extracts a fuzzy argumentative knowledge base, where arguments are explicitly represented as entities, linked by attack and support relations, and annotated with initial fuzzy strengths reflecting plausibility w.r.t. the debate's context. Quantitative argumentation semantics are then applied to compute final argument strengths by propagating the effects of supports and attacks. These results are then embedded into a fuzzy description logic setting, enabling expressive query answering through efficient rewriting techniques. The proposed approach provides a transparent, explainable, and formally grounded method for analyzing debates, overcoming purely statistical LLM-based analyses.