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

2026-02-14

AI Summary

This study addresses the challenge of accurately identifying the pragmatic functions of paraphrasing strategies—such as mitigation, intensification, specification, and generalization—in discourse. To this end, the authors propose a theory-driven multi-agent framework that explicitly integrates argumentation theory into large language models, establishing a novel multidimensional discourse analysis paradigm grounded in the D-I-S-G-O classification scheme. By incorporating retrieval-augmented generation (RAG), the approach enables fine-grained recognition of paraphrasing functions in political debates. Experimental results demonstrate that the proposed method improves the overall Macro F1-score by nearly 30% compared to zero-shot baselines, with particularly pronounced gains in contexts involving intensification and generalization.

Technology Category

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

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• reformulation
• discourse analysis
• pragmatic function
• argumentation
• rhetorical strategies

Innovation

• Retrieval-Augmented Generation
• theoretically-driven LLM agents
• multi-dimensional discourse analysis
• rhetorical reformulation
• argumentation theory