Unverified50% confidenceBenchmarkExact time
In the study, under the best configuration, all four metrics—Recall@3, R-Precision, MRR@3, and nDCG@3—reached 0.94.
1
Sources
50%
Confidence
Long-term
Relevance
10/23/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOn a proprietary dataset, starting from about 3B parameters, the gain brought by fine-tuning is the clearest.65% similarUnverifiedCodebaseRAG's CI gate measures average recall@5, MRR and nDCG@5 on the golden set, and the build fails when average recall@5 falls below the committed baseline of 0.409.64% similarUnverifiedThe best-performing Edu-QuRater achieved an average accuracy of 0.917 in reproducing GPT-4.1-mini pairwise judgments on the held-out set.63% similarUnverifiedThe project introduces three standard retrieval evaluation metrics: Hit Rate, MRR (Mean Reciprocal Rank), and NDCG (Normalized Discounted Cumulative Gain).63% similarUnverifiedThe Top3 configuration achieved an accuracy of 97.148%, a weighted F1 of 97.055%, and an MCC of 0.9675, comprehensively outperforming the Full21 configuration using all 21 metrics (accuracy 95.999%, weighted F1 95.521%, MCC 0.9549).63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1088186API
curl https://kongchang.com/api/v1/knowledge/claims/1088186MCP
get_claim(id=1088186)