Glossary › llms
GLOSSARY
llms
appears in 12 paper titles
Definition
Plural of LLM. Refers to the category as a whole — models pre-trained on large text corpora with next-token prediction, then post-trained to follow instructions — rather than to one checkpoint. Titles use the plural for claims meant to hold across the family. There is no agreed size threshold for "large"; the label tracks the training recipe and resulting generality more than any parameter count.
Explainers using this term
- Paper Walkthrough: HarnessDev — Can an LLM Build and Maintain the System It Runs Inside?HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?
- Evaluating Distilled Models — Is "Close to the Teacher" a Good Metric?The False Promise of Imitating Proprietary LLMs
- Designing Distillation Data — Deciding What to Ask the TeacherDeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning