Unverified50% confidenceFactExact time
At every retrieval pool size setting, Distance-KNN had the highest average accuracy.
1
Sources
50%
Confidence
Long-term
Relevance
10/22/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedTop-1% accuracy is a metric for evaluating the output consistency between a quantized model and the original full-precision model, focusing on whether the top 1% of tokens with the highest model confidence are consistent with the full-precision version.64% similarUnverifiedKITE improves accuracy by up to 23.3 percentage points, with compressed information actually enhancing accuracy.61% similarUnverifiedPrecision Mode leads the strongest frontier model chunk-and-merge baseline solution by 7 percentage points in accuracy.61% similarUnverifiedDirect use of Kev achieves 64.00% accuracy, and Qwen3.5-4B outputting only the final answer achieves 68.80% accuracy.61% similarUnverifiedPrecision Mode achieved an extraction accuracy rate of 94.7% on a benchmark covering approximately 9,000 complex documents.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1084530API
curl https://kongchang.com/api/v1/knowledge/claims/1084530MCP
get_claim(id=1084530)