Unverified50% confidenceBenchmarkExact time
On the same synthetic dataset, the strongest tabular baseline that removes relations and keeps the same signals achieved 81.6% accuracy, with the graph structure bringing about a 14-percentage-point improvement.
1
Sources
50%
Confidence
Long-term
Relevance
10/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn the experiment, unit completion accuracy increased from 72.4% to 84.9%, a gain of 12.5 percentage points.70% similarUnverifiedFor the 7B model, accuracy with the solver was 75.31% versus 72.02% for direct calculation, a paired improvement of +3.29 percentage points, with a 95% cluster interval of [-3.49, 10.38] crossing zero, making the advantage non-significant.69% similarUnverifiedOn the same questions, merely changing the answer extraction method from pattern matching to an explicit \boxed{} format raised accuracy from 20.8% to 93.9%.68% similarUnverifiedIn entity resolution, a shortcut that raised the match rate by ten percentage points had only 38% accuracy against independent identifiers, so it was never released.67% 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67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1054861API
curl https://kongchang.com/api/v1/knowledge/claims/1054861MCP
get_claim(id=1054861)