Unverified50% confidenceFactExact time
Common metrics for recall quality evaluation include Recall@K, MRR (mean reciprocal rank), and hit rate.
1
Sources
50%
Confidence
Long-term
Relevance
10/26/2026
First Seen
Sources
LangChain from Scratch: A Deep Dive into a Hands-On RAG and Agent Tutorial
bilibili大模型学习教程10/26/2026
Related Entities
Related Claims
UnverifiedFor evaluation metrics, retrieval-layer metrics (such as Recall@k and MRR, based on canonical IDs) can be reported separately from generation-layer metrics (fluency and language naturalness).80% similarUnverifiedRetrieval metrics commonly used in RAG evaluation include Hit Rate, Mean Reciprocal Rank (MRR), and Normalized Discounted Cumulative Gain (NDCG).75% similarUnverified回归常用均方误差（MSE）和决定系数（R²）评估，分类用准确率、精确率、召回率和F1值，聚类用轮廓系数等内部评估指标66% similarUnverifiedCommon metrics for measuring review consistency include the standard deviation among review scores and inter-rater reliability coefficients such as Krippendorff's alpha.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1100063API
curl https://kongchang.com/api/v1/knowledge/claims/1100063MCP
get_claim(id=1100063)