Glossary · Term

closed-book

← all terms

Definition

Plain language

Answering a question with no access to outside lookup, just from what the model already learned.

As stated in the literature

An evaluation setting in which a model answers without retrieval or tool access; used as a floor to measure how much benchmark performance comes from parametric knowledge alone.

Also called: closed book

Why it matters: It reveals how much of a benchmark score comes from the model's built-in knowledge versus its ability to look things up, separating recall from research.

For example, asking a model the capital of a country with no internet or documents to consult tests whether it simply memorized the fact during training.

Heard on the show

“And you separate them with the closed-book test.”
Episode 247 — One Edited Photo, an Honest Caption, and a RAG System That Believes It

Mentioned in 6 episodes

  1. 247
    One Edited Photo, an Honest Caption, and a RAG System That Believes It
  2. 214
    The Medical AI Answer That's Accurate, Sourced, and Still Wrong
  3. 099
    How an Open-Book Trick Teaches a Model to Catch Its Own Mistakes
  4. 092
    When Search Agents Don't Really Search: The Memory Shortcut Hiding in Browsing Benchmarks
  5. 090
    How MiniMax-M2 Bets That Sparsity Plus Verifiable Rewards Can Match Frontier Agents
  6. 043
    When 'This Is False' Doesn't Stick: Why Models Learn the Lie Anyway