On Theoretically-Driven LLM Agents for Multi-Dimensional Discourse Analysis

TL;DR

This paper demonstrates that integrating argumentation theory into LLM agents significantly improves their ability to analyze rhetorical functions in discourse, especially in political debates, by using a multi-agent framework with retrieval-augmented generation.

Contribution

It introduces a multi-agent framework that incorporates theoretical knowledge to enhance LLMs' detection of discourse functions, outperforming baseline models in argumentative discourse analysis.

Findings

RAG-enhanced agents outperform zero-shot baseline in detecting discourse functions.

Significant improvement in identifying Intensification and Generalisation functions.

Overall Macro F1-score improves by nearly 30%.

Abstract

Identifying the strategic uses of reformulation in discourse remains a key challenge for computational argumentation. While LLMs can detect surface-level similarity, they often fail to capture the pragmatic functions of rephrasing, such as its role within rhetorical discourse. This paper presents a comparative multi-agent framework designed to quantify the benefits of incorporating explicit theoretical knowledge for this task. We utilise an dataset of annotated political debates to establish a new standard encompassing four distinct rephrase functions: Deintensification, Intensification, Specification, Generalisation, and Other, which covers all remaining types (D-I-S-G-O). We then evaluate two parallel LLM-based agent systems: one enhanced by argumentation theory via Retrieval-Augmented Generation (RAG), and an identical zero-shot baseline. The results reveal a clear performance gap: the RAG-enhanced agents substantially outperform the baseline across the board, with particularly strong advantages in detecting Intensification and Generalisation context, yielding an overall Macro F1-score improvement of nearly 30\%. Our findings provide evidence that theoretical grounding is not only beneficial but essential for advancing beyond mere paraphrase detection towards function-aware analysis of argumentative discourse. This comparative multi-agent architecture represents a step towards scalable, theoretically informed computational tools capable of identifying rhetorical strategies in contemporary discourse.