Unverified50% confidenceBenchmarkExact time
On the Natural Plan benchmark without task-specific training, the diffusion model's plan repair success rate was 53.7%, while the autoregressive model's was 27.0%.
1
Sources
50%
Confidence
Long-term
Relevance
10/9/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe 7 models that passed the surrogate test had a change rate of 15.9%, while the 6 models that did not pass had a rate as high as 25.8%, indicating that better-performing models are less susceptible to interference but still more so than the effect of prompt modification.66% similarUnverifiedIn the experiment where the 27B model wrote its own skills, it scored 56.3% on LiveMath.65% similarUnverifiedAnthropic's research shows that even mild alignment training can cause a 2–8 percentage point decline in model performance on certain reasoning-intensive tasks.64% similarUnverified研究表明采用减害策略的干预项目其12个月后的行为改善保持率通常比完全戒断项目高出30-50%64% similarUnverifiedAfter matched supervised training, model performance improved to 99.8%, while removing the relational links caused accuracy to plummet to 23.4%, even below the best shortcut's 27.0%.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/990478API
curl https://kongchang.com/api/v1/knowledge/claims/990478MCP
get_claim(id=990478)