Unverified50% confidenceSolutionExact time
When fine-tuning embedding models, hard negatives (such as positions in the same domain but at different levels) should be used instead of random negatives, in order to learn more fine-grained semantic differences.
1
Sources
50%
Confidence
Long-term
Relevance
8/31/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedFine-tuning embedding models with contrastive learning requires labeled data (positive samples of successful hires and negative samples of rejected candidates) to achieve significant performance gains.77% similarUnverifiedWhen selecting models, one should not only look at accuracy on standard datasets but also pay attention to out-of-domain generalization robustness on unfamiliar data.75% similarUnverified生成模型在小样本时更具优势，判别模型在大数据量时通常表现更好74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/831140API
curl https://kongchang.com/api/v1/knowledge/claims/831140MCP
get_claim(id=831140)