{
  "id": 19434,
  "url": "https://arxiv.org/abs/2608.13545v1",
  "title": "LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure",
  "summary": "Modern language models are trained on heterogeneous web-scale text corpora. Consequently, studying knowledge and skill acquisition is difficult, as prior exposure to related content is hard to characterize. To address this challenge, we introduce LITTLECURRICULUM, a curated 88B-token pretraining corpus tailored to U.S. elementary school material, explicitly excluding concepts, facts, and vocabulary taught above Grade 5. Training a 5B-parameter LLM from scratch on LITTLECURRICULUM yields LITTLELE",
  "authors": "Fanfei Li, Jana Zeller, Manuel Prada-Corral, Thaddäus Wiedemer, Prasanna Mayilvahanan, Ryan Cotterell, Wieland Brendel",
  "category": "research",
  "topics": "children-education",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-13T17:56:12.000Z",
  "fetched_at": "2026-08-14T05:10:49.168Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/19434",
  "original_url": "https://arxiv.org/abs/2608.13545v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}