When Long Helps Short: How Context Length in Supervised Fine-tuning Affects Behavior of Large Language Models

Documenti analoghi

• How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition
  di: Dong, Guanting, et al.
  Pubblicazione: (2023)
• LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
  di: Chen, Yukang, et al.
  Pubblicazione: (2023)
• How does Misinformation Affect Large Language Model Behaviors and Preferences?
  di: Peng, Miao, et al.
  Pubblicazione: (2025)
• Evolving Subnetwork Training for Large Language Models
  di: Li, Hanqi, et al.
  Pubblicazione: (2024)
• Fine-tuning can Help Detect Pretraining Data from Large Language Models
  di: Zhang, Hengxiang, et al.
  Pubblicazione: (2024)