Single-Token Expected-Value Scoring for Cold-Start Candidate Ranking
A fine-tuned Small Language Model is fine-tuned with a hybrid ordinal regression loss combining a Mean Squared Error term, which preserves ordinal distance, with a categorical Cross-Entropy term, which sharpens class boundaries, which sharpens class boundaries.
Qi-Hang Wang, Jin-Wei Tan, Meng-Yuan Shi et al.
· 0 citations