AI Paper Atlas

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

The Inductive Bias of In-Context Learning: Rethinking Pretraining Example Design

Yoav Levine, Noam Wies, Daniel Jannai, Dan Navon, Yedid Hoshen, Amnon Shashua

ICLR 2022 · Large language models › Language, safety and interpretability · approach: In-context learning analysis · 1 citations (OpenAlex)

Read the paper

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
Append retrieved Wikipedia neighbors in-context during TAPT rather than using regular TAPTRoBERTa-base · SentEval sentence similarity (Avg.)sentence similarity score: 59.8 -> 61.0Improved
Use retrieved neighbors in separate in-batch examples rather than regular TAPT (ablation)RoBERTa-base · SentEval sentence similarity (Avg.)sentence similarity score: 59.8 -> 58.8Hurt
Use random Wikipedia sentences in separate in-batch examples rather than regular TAPT (ablation)RoBERTa-base · SentEval sentence similarity (Avg.)sentence similarity score: 59.8 -> 58.4Hurt
Append random Wikipedia sentences in-context rather than using regular TAPT (ablation)RoBERTa-base · SentEval sentence similarity (Avg.)sentence similarity score: 59.8 -> 60.0No clear effect
Use retrieved neighbors in-context rather than retrieved neighbors in separate in-batch examples (ablation)kNN-TAPT · SentEval sentence similarity (Avg.)sentence similarity score: 58.8 -> 61.0Improved
Use retrieved neighbors rather than random Wikipedia sentences in-context (ablation)kNN-TAPT · SentEval sentence similarity (Avg.)sentence similarity score: 60.0 -> 61.0Improved
Add kNN-Pretraining after regular Wikipedia pretrainingGPT-2-medium · Natural Questions open-domain QA, zero-shot closed-bookcorrect answers: less than 50 -> roughly 250Improved

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