AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Localizing Task Recognition and Task Learning in In-Context Learning via Attention Head Analysis

Haolin Yang, Hakaze Cho, Naoya Inoue

ICLR 2026 · Architectures and efficiency › Attention and transformers · approach: Training dynamics of in-context learning · 2 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
ablate top 3% TR heads (ablation)LLM in-context learning · 7 classification datasets (avg)TR ratio: nearly 100% -> ~20%Hurt
ablate top 3% TL heads (ablation)LLM in-context learning · 7 classification datasets (avg)accuracy: lowers accuracy by ~30%Hurt
ablate top 3% TL heads (ablation)LLM in-context learning · 7 classification datasets (avg)TR ratio: reduces TR ratio by ~10%Hurt
select heads with TSLA instead of Direct Logit Attribution (ablation)TL head identification · 7 datasets, Llama3-8Bablation effect (accuracy toward random guessing)Improved
add TR-based task vectors to zero-shot inputszero-shot LLM · classification datasetszero-shot accuracyImproved
add TL-based task vectors instead of TR or randomzero-shot generation · sentiment review generationLLM rating 0-10Improved
steer with TR head outputshidden states · ICL promptssubspace alignmentImproved

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