LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure

  • 类型：arxiv
  • 标识：2608.13545
  • 链接：https://arxiv.org/abs/2608.13545
  • 主分类：engineering
  • 形态：method
  • 被引：0
  • 被引来源：Semantic Scholar
  • S2被引：0
  • 影响力被引：0
  • TLDR：This work introduces LITTLECURRICULUM, a curated 88B-token pretraining corpus tailored to U.S. elementary school material, which yields LITTLELEARNER, a model with sufficient language competence for open-ended evaluation, yet with clear knowledge and capability boundaries mapped to interpretable curriculum guidelines.
  • 待LLM分类：否
  • 标题中文：LittleLearner：在教学受控知识暴露下的语言模型
  • TLDR中文：提出 LITTLECURRICULUM，一个为美国小学课程量身定制的 88B token 精选预训练语料，并由此训练得到 LITTLELEARNER；该模型具备开放式评估所需的语言能力，同时其知识和能力边界清晰可映射到可解释的课程指南。
  • 来源文件：
  • /inbox/tom/_candidates/2026-08-17-agent-rag-longcontext-candidates.json
  • [S2 enrich]