DCIS: Efficient Length Extrapolation of LLMs via Divide-and-Conquer Scaling Factor Search

Documenti analoghi

• LANDeRMT: Detecting and Routing Language-Aware Neurons for Selectively Finetuning LLMs to Machine Translation
  di: Zhu, Shaolin, et al.
  Pubblicazione: (2024)
• Efficiently Exploring Large Language Models for Document-Level Machine Translation with In-context Learning
  di: Cui, Menglong, et al.
  Pubblicazione: (2024)
• Self-Pluralising Culture Alignment for Large Language Models
  di: Xu, Shaoyang, et al.
  Pubblicazione: (2024)
• Enhancing LLM Character-Level Manipulation via Divide and Conquer
  di: Xiong, Zhen, et al.
  Pubblicazione: (2025)
• ConTrans: Weak-to-Strong Alignment Engineering via Concept Transplantation
  di: Dong, Weilong, et al.
  Pubblicazione: (2024)