Unverified50% confidenceBenchmarkExact time
The most aggressive configuration achieves an average token reduction rate of 40.3% (standard deviation 9.2), with a BERTScore-F1 of 0.876 relative to the output of the original prompt
1
Sources
50%
Confidence
Long-term
Relevance
9/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe stopword-removal-only configuration can achieve a token reduction of 29.6% while maintaining a BERTScore-F1 of 0.91371% similarUnverifiedCriticGen's F1 scores on criteria-based rationales and actionable suggestions improved from 0.6369/0.5994 to 0.7554/0.7900, respectively.66% similarUnverifiedIn guided mode, the average end-to-end accuracy increased from 28.6% to 33.7%, and the ambiguity detection F1 score increased from 45.3% to 64.9%65% similarUnverifiedCompared to FP16 original precision, FP8 quantization typically causes no more than 1–2% performance degradation on mainstream benchmarks.62% similarUnverifiedDevelopers ultimately selected the variant with the lowest KL divergence (0.028), resulting in a 1.83% drop on GSM8K, no change on MMLU, and an improvement in HarmBench compliance rate from 30.8% to 100%61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/921792API
curl https://kongchang.com/api/v1/knowledge/claims/921792MCP
get_claim(id=921792)