Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2602.13713 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910055038713856 |
|---|---|
| author | Uberna, Maciej Wawer, Michał Chudziak, Jarosław A. Koszowy, Marcin |
| author_facet | Uberna, Maciej Wawer, Michał Chudziak, Jarosław A. Koszowy, Marcin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_13713 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | On Theoretically-Driven LLM Agents for Multi-Dimensional Discourse Analysis Uberna, Maciej Wawer, Michał Chudziak, Jarosław A. Koszowy, Marcin Computation and Language 91G68 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. |
| title | On Theoretically-Driven LLM Agents for Multi-Dimensional Discourse Analysis |
| topic | Computation and Language 91G68 |
| url | https://arxiv.org/abs/2602.13713 |