Metraipolis › archive › dc_ca419da7a85b
Benchmarking Argumentative Behaviour of LLMs: A Study of Defences Against Character Attacks — arXiv:2609.28673
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.28673
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T04:49:23.691Z
- SHA-256 of the archived text
0fb9716bf033e717483e39c3136e334e8160043e3e25400a5eaf3e188c915380- Stable URL of this page
https://metraipolis.com/documento/dc_ca419da7a85b
How to cite
Benchmarking Argumentative Behaviour of LLMs: A Study of Defences Against Character Attacks — arXiv:2609.28673 — arXiv (en), https://arxiv.org/abs/2609.28673 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ca419da7a85b (Metraipolis archive dc_ca419da7a85b, sha256 0fb9716bf033e717483e39c3136e334e8160043e3e25400a5eaf3e188c915380)
BibTeX
@misc{dcca419da7a85b,
title = {Benchmarking Argumentative Behaviour of LLMs: A Study of Defences Against Character Attacks — arXiv:2609.28673},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.28673},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ca419da7a85b; sha256 0fb9716bf033e717483e39c3136e334e8160043e3e25400a5eaf3e188c915380},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28673. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large Language Models (LLMs) are increasingly deployed as argumentative agents in persuasive dialogues, necessitating rigorous evaluation of their debating competence relative to human interlocutors. In this study, we focus on character attacks (ad hominem arguments), traditionally dismissed as fallacies, which play a pivotal role in political persuasive dialogues where ethos often rivals propositional content. Specifically, we investigate whether modern LLMs can replicate human competence to strategically use and respond to such attacks. We analyse a corpus of natural language political dialogues to identify defensive strategies human interlocutors naturally employ in ethos-centred debates and structure them into a dialogue game. Empirically, we benchmark LLM-generated dialogues against the ElecDeb60to16-fallacy corpus of U.S. presidential debates, contrasting human debaters' repertoire of defensive strategies with those of artificial agents. Results reveal a substantial difference: most LLMs rigidly prioritise logical defences, failing to exploit ethotic counterattacks as valid moves in political discourse. We argue that current safety fine-tuning constraints the strategic action space of these LLMs, making them unable to fully engage in naturalistic interactions within domains where character contestation is a normative expectation rather than a mere fallacy. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.28673 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T04:27:20.016Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).