Unverified50% confidenceBenchmarkExact time
In the SST-2 dataset DistilBERT-to-DistilBERT self-distillation experiment, the reliability gating method achieved 88.800%, RAPID achieved 88.685%, representing an improvement of approximately 1.4 percentage points over the baseline of 87.271%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
UnverifiedIn the BERT-to-DistilBERT distillation experiment on the AG News dataset, reliability-gated relation distillation achieved an accuracy of 94.285±0.054%, and RAPID achieved 94.241±0.025%, both outperforming the cross-entropy baseline of 94.154±0.124%71% similarUnverified探索性能上界实验发现现有验证粒度并非最优，理想情况下计算量（FLOPs）可减少75倍，同时准确率提升1.1%66% similarUnverifiedFastEmbed-rs所使用的量化模型在MTEB基准测试中相比全精度模型的性能下降通常控制在1-2%以内65% similarUnverifiedOn the BrowseWebApp Bench benchmark, the accuracy of the fine-tuned model improved from 22% to 63%.64% similarUnverifiedFan's team's performance upper-bound experiment found that under ideal conditions, computational FLOPs can be reduced by 75×, while accuracy improves by 1.1%.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/895499API
curl https://kongchang.com/api/v1/knowledge/claims/895499MCP
get_claim(id=895499)