Unverified50% confidenceFactExact time
When fine-tuned on samples of safe refusals, the model learns refusal as a tendency, which may lead it to over-refuse legitimate questions as well.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedA refusal-to-answer mechanism triggers a degradation strategy—such as returning an uncertain response, requesting human review, or narrowing the scope of the answer—when it detects that the input is out of the training distribution or the model's confidence is below a threshold.79% similarVerifiedExcessive safety fine-tuning can cause models to over-refuse, undermining their practical utility.77% similarUnverifiedSelf-generated feedback from the model may produce misleading pseudo-insights, and validator quality affects feedback effectiveness, which remains an open question for this method.77% similarUnverifiedUncensored models remove or weaken overly conservative refusal behavior, thereby providing more practical technical output in security scenarios.76% similarVerifiedOver-refusal strategies reduce risk but harm model utility, especially in scenarios such as professional development and security research that require touching sensitive boundaries.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1069890API
curl https://kongchang.com/api/v1/knowledge/claims/1069890MCP
get_claim(id=1069890)