In-context learning
HoldTechniques
Prompt-based adaptation where the model uses examples in the input context without weight updates.
Why it's here
Placed in Hold: 1 article(s) of evidence from 1 source(s), led by research-stage coverage, with 0 in the last 30 days. Confidence 24%. Low accumulated evidence, so it defaults conservatively pending more signal.
Evidence (1)
- 7Hacker News·8/16/2026researchLittleLearner studies LLMs trained only on K–5 material
Researchers introduced LittleLearner, a set of language models trained from scratch on an 88B-token corpus filtered to U.S. elementary-school curriculum content up to grade 5. The study finds that scaling, post-training, and in-context learning improve in-scope performance but do not meaningfully extend capability beyond the curated knowledge boundary.