LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure

arXiv:2608.13545v1 Announce Type: cross Abstract: 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 LITTLELEARNER, a model with sufficient language competence for open-ended evaluation, yet with clear knowledge and capability boundaries mapped to interpretable curriculum guidelines. We release LITTLECURRICULUM and LITTLELEARNER as a developmentally restricted sandbox to study how models acquire, represent, and use data under a well-defined training scope. We illustrate the sandbox's utility in a first suite of experiments on injecting new knowledge through post-training and in-context learning. These methods let LITTLELEARNER better utilize existing knowledge, but do not raise out-of-scope capabilities. Our findings underscore the value of this controlled environment for future investigations.

Related

• CAP: Controllable Alignment Prompting for Unlearning in LLMs
• TFGN: Task-Free, Replay-Free Continual Pre-Training Without Catastrophic Forgetting at LLM Scale

Source: arXiv cs.AI | 2026-08-14