Rules Amortize, Pairings Don't: Linguistic Structure Determines What Latent Task Representations Can Replace In-Context Learning

arXiv:2610.00526 · cs.CL, cs.AI · Submitted 2026-09-30 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-09-30

Updated: 2026-09-30

Terminology

• In-Context Learning — 7× in this paper · explained in 4 episodes
• Accuracy — 6× in this paper · explained in 1 episode
• Amortization — 2× in this paper · explained in 1 episode
• Frozen model — 2× in this paper · explained in 3 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Few-Shot Learning — 1× in this paper · explained in 4 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• In-Context Learning (ICL) — 1× in this paper · explained in 5 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Steering — 1× in this paper · explained in 2 episodes

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering