🧪 Test?View on arXiv
Benchmarking Argumentative Behaviour of LLMs: A Study of Defences Against Character Attacks
Author1, Author2, Author3, Author4, Author5
argumentationcharacter attacksdebateLLM evaluation
2609.28673
Builder Relevance
1h ago70%
Abstract
This study evaluates the argumentative competence of LLMs in the context of character attacks in political dialogues.
Reality Card
Core Claim
Most LLMs prioritize logical defenses over ethotic counterattacks, revealing a significant gap in their ability to engage in naturalistic political discourse.
Method / Result
LLMs were benchmarked against the ElecDeb60to16-fallacy corpus, showing a substantial difference in defensive strategies compared to human debaters.
Limitations
Current safety fine-tuning constrains LLMs' strategic action space, limiting their engagement in character contestation.
Paper to code
Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.
No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.