Unverified50% confidenceBenchmarkExact time
In the ablation study, when no data is used and only parametric memory is relied on, even the best model performs poorly; after providing early-quarter data, performance improves by about 25 percentage points; but there is still a 12-16 percentage point gap from using the latest data.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
Unverified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73% similarUnverifiedFor small models with limited parameter counts, data quality can have an even greater impact on final performance than data quantity.73% similarUnverifiedIn many evaluations conducted on small datasets, scores fluctuate by several percentage points across different runs.72% similarUnverifiedThe 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.72% similarUnverifiedWhen models were provided with complete company records, strict accuracy actually dropped from 41% to 18%, while recall rose and precision collapsed.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1011138API
curl https://kongchang.com/api/v1/knowledge/claims/1011138MCP
get_claim(id=1011138)