Gradients Must Earn Their Influence: Unifying SFT with Generalized Entropic Objectives

Documenti analoghi

• Beyond Confidence: The Rhythms of Reasoning in Generative Models
  di: Liu, Deyuan, et al.
  Pubblicazione: (2026)
• Checkpoint Merging via Bayesian Optimization in LLM Pretraining
  di: Liu, Deyuan, et al.
  Pubblicazione: (2024)
• Mitigating Gender Bias in Code Large Language Models via Model Editing
  di: Qin, Zhanyue, et al.
  Pubblicazione: (2024)
• Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging
  di: Liu, Deyuan, et al.
  Pubblicazione: (2024)
• LFTF: Locating First and Then Fine-Tuning for Mitigating Gender Bias in Large Language Models
  di: Qin, Zhanyue, et al.
  Pubblicazione: (2025)