Unverified50% confidenceFactExact time
The correlation between ADMET prediction models and real in vivo experiments is often limited.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen a predictive model performs excellently but clinicians cannot take practical action based on it, its impact on outcomes may be minimal.66% similarUnverifiedOn the strongest models, the differences between experimental groups fall within confidence intervals, and researchers characterized the results as directional patterns and soundness properties rather than proven performance lower bounds66% similarUnverifiedQi et al. (ICLR 2024) observed that as few as a small number of adversarial samples can cause model alignment degradation, with even benign datasets producing a smaller negative effect.66% similarUnverifiedAlthough sample splitting guarantees the theoretical properties, it reduces the sample size used to compute the test statistic, which may weaken test power in small-sample settings.65% similarUnverifiedExperiments show that models processed with abliteration exhibit almost no degradation on standard capability evaluations, but the probability of refusing harmful requests drops significantly.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1069524API
curl https://kongchang.com/api/v1/knowledge/claims/1069524MCP
get_claim(id=1069524)