Efficient Continual Pre-training by Mitigating the Stability Gap

Documenti analoghi

• Evidence-Enhanced Triplet Generation Framework for Hallucination Alleviation in Generative Question Answering
  di: Du, Haowei, et al.
  Pubblicazione: (2024)
• Synthetic Data RL: Task Definition Is All You Need
  di: Guo, Yiduo, et al.
  Pubblicazione: (2025)
• PPTC-R benchmark: Towards Evaluating the Robustness of Large Language Models for PowerPoint Task Completion
  di: Zhang, Zekai, et al.
  Pubblicazione: (2024)
• Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes
  di: Gong, Zhuocheng, et al.
  Pubblicazione: (2025)
• Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training
  di: Du, Wenyu, et al.
  Pubblicazione: (2024)