Unverified50% confidenceBenchmarkExact time
In 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%
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOn the CLINC150 benchmark, 80 fine-tuning samples can bring vector routing to an accuracy of 85.9%, while a full fine-tune can exceed 96%.72% 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%69% similarUnverifiedTraditional vector RAG generally achieves an accuracy rate of 68%–72% in complex multi-hop query scenarios.67% 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%.66% similarUnverifiedThe per-step accuracy of current top-tier models is approximately between 90% and 95%.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/893412API
curl https://kongchang.com/api/v1/knowledge/claims/893412MCP
get_claim(id=893412)