AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

The Coverage Principle: How Pre-Training Enables Post-Training

Fan Chen, Audrey Huang, Noah Golowich, Sadhika Malladi, Adam Block, Jordan T. Ash, Akshay Krishnamurthy, Dylan J Foster

ICLR 2026 · Large language models › Language, safety and interpretability · approach: LLM pruning and scaling data · 28 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
continue minimizing cross-entropy in later training on a two-class mixed graph taskGPT-2-style transformer · graph search (layered DAG, mixture of two classes)coverage profile / Best-of-NHurt
use a mid-training checkpoint selected by coverage rather than the final low-cross-entropy checkpointpre-trained transformer · graph searchcoverage profileImproved
increase sequence horizon H (8, 16, 24)next-token prediction · graph searchKL divergence vs coverage profileMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy