Unverified50% confidenceBenchmarkExact time
SAFE-QE was evaluated on two benchmark retrieval collections, TREC and BEIR.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedQ2D-Web introduces three mutually independent sets of relevance judgments to cross-validate the quality of retrieval results.63% similarUnverifiedCommon alignment evaluation benchmarks include TruthfulQA and HarmBench.62% similarUnverifiedCVE-Bench is based on publicly disclosed CVE entries and tests a model's ability to identify, classify, and analyze the exploitability of known vulnerabilities.61% similarUnverifiedFunnel-style layered evaluation architecture: the first layer uses cheap and fast semantic verifiers to pre-screen large volumes of traces, and the second layer passes ambiguous or high-value samples to a more powerful judge model for detailed evaluation.61% similarUnverifiedQwQ-32B第二阶段使用通用奖励模型和基于规则的验证器两种验证机制进行通用能力扩展60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1002088API
curl https://kongchang.com/api/v1/knowledge/claims/1002088MCP
get_claim(id=1002088)