ChronoLens: Measuring Language Change Across Time, Languages, and Linguistic Levels

  • 类型:arxiv
  • 标识:2608.03507
  • 链接:https://arxiv.org/abs/2608.03507
  • 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:ChronoLens is introduced, a framework that combines frozen multilingual language models, feature-aligned crosscoders, and post-hoc linguistic interventions, and applies it to 44.98 million documents and approximately 17.2 billion tokens from five parliamentary traditions spanning 1803--2026, showing that historical language change is a structured, multidimensional process.
  • 待LLM分类:否
  • 标题中文:ChronoLens: 跨时间、语言与语言学层面的语言变化测量
  • TLDR中文:提出 ChronoLens,结合冻结的多语言语言模型、特征对齐的 crosscoder 与事后语言学干预,应用于来自五个议会传统、跨越 1803–2026 年的 4498 万篇文档和约 172 亿 tokens,表明历史语言变化是一个结构化的、多维度的过程。
  • 成熟度:research
  • 场景:语言演化测量、跨语言历时分析
  • 来源文件
  • /inbox/tom/_candidates/2026-08-06-agent-rag-longcontext-candidates.json
  • [S2 enrich]