Unverified50% confidenceBenchmarkExact time
Under an 18k character budget, anchored hybrid retrieval achieved 36.18% accuracy, BM25 achieved 35.98%, while the best direct planner-guided method reached only 34.19%.
1
Sources
50%
Confidence
Long-term
Relevance
9/24/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe locally run Gemma 26B achieved an accuracy of only 49.2% across 453 scored predictions, while its paired always-predict-up baseline had an accuracy of 53.4%.72% similarUnverified生产中典型做法是先用向量检索和BM25快速召回50-100个候选结果，再用reranker精排取top-k送入LLM71% similarUnverifiedIn the LongMemEval benchmark, BM25 accuracy improved from 78.8% to 85.2% with 5 chunks.70% 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%68% similarUnverifiedState-of-the-art supervised models on the LIAR benchmark still hover around 28%–32% six-class accuracy.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/946181API
curl https://kongchang.com/api/v1/knowledge/claims/946181MCP
get_claim(id=946181)