Unverified50% confidenceBenchmarkExact time
Causal probes achieved a 17%–118% improvement in steering capability across different models, with only a 3% decrease in concept detection capability.
1
Sources
50%
Confidence
Long-term
Relevance
10/7/2026
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.75% similarUnverifiedThe research team pointed out that the performance gains from inference-time context management in benchmarks exceeded most system-to-system differences that have been reported.74% similarUnverified靶向数据工程中，针对性数据占总微调数据的 5%-15% 通常能取得良好效果，过高比例可能导致模型在其他维度退化72% similarUnverified研究人员发现，仅将函数描述中的retrieve替换为fetch，在某些模型上会导致调用成功率下降约15%71% 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.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/982948API
curl https://kongchang.com/api/v1/knowledge/claims/982948MCP
get_claim(id=982948)