Unverified50% confidenceFactExact time
Previous research has mostly attributed over-refusal to static representation overlap, where benign prompts and harmful prompts are too close to each other in the model's internal representation space.
1
Sources
50%
Confidence
Long-term
Relevance
9/23/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedExcessive safety fine-tuning can cause models to over-refuse, undermining their practical utility.75% similarVerifiedSome models carry the risk of over-optimization toward test sets, causing leaderboard scores to deviate from real-world performance (benchmark saturation).75% similarVerifiedDrift detection involves a trade-off: setting the threshold too sensitively leads to frequent false alarms and unnecessary retraining, while setting it too loosely may allow model performance to continuously degrade without being detected.73% similarUnverifiedWhen reasoning moves silently into latent space, the model's thinking process becomes less transparent, reducing interpretability and posing new challenges for AI safety and alignment research.73% similarUnverifiedVersion drift is dangerous in evaluation scenarios because the validity of historical measurement results implicitly decays after changes to model weights, inference frameworks, or test environments73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/942932API
curl https://kongchang.com/api/v1/knowledge/claims/942932MCP
get_claim(id=942932)