FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain

Documenti analoghi

• Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe
  di: Thekumparampil, Kiran Koshy, et al.
  Pubblicazione: (2024)
• An Efficient Plugin Method for Metric Optimization of Black-Box Models
  di: Devic, Siddartha, et al.
  Pubblicazione: (2025)
• Logits are All We Need to Adapt Closed Models
  di: Hiranandani, Gaurush, et al.
  Pubblicazione: (2025)
• Language-Model Prior Overcomes Cold-Start Items
  di: Wang, Shiyu, et al.
  Pubblicazione: (2024)
• SED-SFT: Selectively Encouraging Diversity in Supervised Fine-Tuning
  di: Chen, Yijie, et al.
  Pubblicazione: (2026)