HomeResearch LibraryLong-Context Language Models: A Survey
surveyChapter 2arXiv · 2024

Long-Context Language Models: A Survey

Tianlong Chen (MIT), Xuxi Chen (UT Austin)

Abstract

We survey methods for extending the context length of language models, covering positional encoding extensions, efficient attention mechanisms, and memory-augmented architectures.

Key Contributions

  • Long-context methods survey
  • Positional encoding extensions
  • Efficient attention mechanisms

Topics

long contextcontext lengthefficient attentionmemory