Gathered, Not Admitted: How Attention Brings a Latent Variable into Verbalizable Form

  • 类型:arxiv
  • 标识:2608.15022
  • 链接:https://arxiv.org/abs/2608.15022
  • 主分类:evaluation
  • 形态:benchmark
  • 被引:0
  • 被引来源:Semantic Scholar
  • S2被引:0
  • 影响力被引:0
  • TLDR:Language models hold latent quantities in a form they can report on, and more of a quantity is present in that form when the task requires reusing it flexibly when the task requires reusing it flexibly.
  • 待LLM分类:否
  • 标题中文:Gathered, Not Admitted:注意力如何将潜变量带入可言语化的形式
  • TLDR中文:语言模型以一种可被报告的形式持有潜在量,并且当任务需要灵活复用该量时,更多该量的信息会以这种形式存在。
  • 来源文件
  • /inbox/tom/_candidates/2026-08-18-agent-rag-longcontext-candidates.json
  • [S2 enrich]