AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

In-Context Algebra

Eric Todd, Jannik Brinkmann, Rohit Gandikota, David Bau

ICLR 2026 · Architectures and efficiency › Attention and transformers · approach: Transformer expressivity and learnability · 7 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
increase hidden dimension from 128 to 1024 (ablation)In-context algebra transformer · held-out evalevaluation accuracy: 13.3% -> 99.4%Improved
increase hidden dimension from 256 to 512 (ablation)In-context algebra transformer · held-out evalevaluation accuracy: 61.3% -> 96.9%Improved
increase hidden dimension from 1024 to 2048 (ablation)In-context algebra transformer · held-out evalevaluation accuracy: 99.4% -> 98.6%No clear effect
increase layers from 2 to 4 (ablation)In-context algebra transformer · held-out evalevaluation accuracy: 93.5% -> 99.4%Improved
increase layers from 4 to 10 (ablation)In-context algebra transformer · held-out evalevaluation accuracy: 99.4% -> 98.8%No clear effect
increase heads from 4 to 8 (ablation)In-context algebra transformer · held-out evalevaluation accuracy: 95.9% -> 99.4%Improved
increase heads from 2 to 8 (ablation)In-context algebra transformer · held-out evalevaluation accuracy: 99.2% -> 99.4%No clear effect
vary depth for associativity sequences (ablation)In-context algebra transformer · associativity subsetassociativity score: 85.9% (4 layers) vs 51.6% (8 layers)Mixed
raise group mixing probability p_mix (ablation)In-context algebra transformer · held-out evalevaluation accuracyImproved
raise group mixing probability p_mix (ablation)In-context algebra transformer · trainingtime to generalizationImproved
evaluate on unseen order-8 groups vs in-distribution groupsIn-context algebra transformer · unseen groupsaccuracyNo clear effect
evaluate on quasigroups instead of groupsIn-context algebra transformer · held-out unseen structuresaccuracy: up to 50% at 200 factsHurt

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