First is Not Really Better Than Last: Evaluating Layer Choice and Aggregation Strategies in Language Model Data Influence Estimation

Documenti analoghi

• LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions
  di: Askari, Hadi, et al.
  Pubblicazione: (2025)
• Less Diverse, Less Safe: The Indirect But Pervasive Risk of Test-Time Scaling in Large Language Models
  di: Nahin, Shahriar Kabir, et al.
  Pubblicazione: (2025)
• Revisiting the Effectiveness of LLM Pruning for Test-Time Scaling
  di: Monjur, Ocean, et al.
  Pubblicazione: (2026)
• Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis
  di: Datta, Shrestha, et al.
  Pubblicazione: (2026)
• Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment
  di: Zhang, Jiazheng, et al.
  Pubblicazione: (2025)