Unverified50% confidenceFactExact time
The study finds that most LLMs rigidly prioritize logical defenses and almost never use character counterattacks as a means of action in political discourse.
1
Sources
50%
Confidence
Long-term
Relevance
9/25/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedExplainability can be exploited adversarially — once an adversary understands the model's decision logic, they can design evasion strategies.73% similarUnverifiedPrevious evaluations of LLMs' debating capabilities have largely focused on factual accuracy and logical coherence, while neglecting social rhetorical dimensions such as ethos and pathos.71% similarUnverifiedPrevious research on LLM moral judgment has largely been based on two unrealistic assumptions: single-turn judgment and pressure-based rebuttal.70% similarUnverifiedThe paper argues that in legal contexts, declining to answer or signaling uncertainty is often more responsible than forcing a seemingly complete answer, which contrasts with the current tendency of LLMs to always provide an answer.70% similarUnverifiedThe refusal reasons generated by language models may be fabricated rationalizations (hallucinations) rather than being based on explicit safety policies67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/949130API
curl https://kongchang.com/api/v1/knowledge/claims/949130MCP
get_claim(id=949130)