Unverified50% confidenceBenchmarkExact time
On the two tasks of LEMMO-LongDesc, LEMMO improved both classification and numerical fact F1.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/9/2026
First Seen
Valid until: 2/7/2027
Sources
Related Entities
Related Claims
UnverifiedCertifying the improvement of a decision relative to an informative incumbent policy requires O(l⁻²) new records drawn from the same observation law.57% similarUnverifiedSelecting few-shot examples based on semantic similarity and increasing the number of examples can raise the LLM's F1 score on the hard test set by nearly 10 points over the baseline configuration.57% similarUnverifiedIn class-imbalanced scenarios, the F1 score better reflects the model's ability to recognize the minority class than accuracy does.57% similarUnverifiedEXL2 支持混合精度量化,按重要性为不同权重分配位宽,在相同平均位宽下往往比同等 GGUF 模型在精度敏感任务上表现更优56% similarUnverifiedIn multi-class tasks, accuracy becomes distorted when class samples are imbalanced; precision reflects the degree of false positives, recall reflects the degree of false negatives, and the F1 score is the harmonic mean of precision and recall.56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1149674API
curl https://kongchang.com/api/v1/knowledge/claims/1149674MCP
get_claim(id=1149674)