Minimal Ranks, Maximum Confidence: Parameter-efficient Uncertainty Quantification for LoRA
Tytuł:
Minimal Ranks, Maximum Confidence: Parameter-efficient Uncertainty Quantification for LoRA
Konferencja:
Empirical Methods in Natural Language Processing [EMNLP]
Rok:
2025
Opis:
https://ruj.uj.edu.pl/handle/item/567919
Strony:
1260-1271
Numer DOI:
https://doi.org/10.18653/v1/2025.findings-emnlp.66
Link:
https://aclanthology.org/2025.findings-emnlp.66/