Understanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation Transitions

Documenti analoghi

• XPERT: Expert Knowledge Transfer for Effective Training of Language Models
  di: Liu, Chang, et al.
  Pubblicazione: (2026)
• LaCo: Large Language Model Pruning via Layer Collapse
  di: Yang, Yifei, et al.
  Pubblicazione: (2024)
• Chain-based Distillation for Effective Initialization of Variable-Sized Small Language Models
  di: Shi, Boyu, et al.
  Pubblicazione: (2026)
• GPTailor: Large Language Model Pruning Through Layer Cutting and Stitching
  di: Su, Guinan, et al.
  Pubblicazione: (2025)
• Progressively Label Enhancement for Large Language Model Alignment
  di: Liu, Biao, et al.
  Pubblicazione: (2024)