Capturing In-Context Learning Dynamics with Task Operators

arXiv:2610.01054 · cs.CL, cs.AI, cs.LG · Submitted 2026-10-01 · Read on arXiv

cs.CL, cs.AI, cs.LG

Submitted: 2026-10-01

Updated: 2026-10-01

Code: https://github.com/gzxiong/task_operator

Terminology

• In-Context Learning — 23× in this paper · explained in 4 episodes
• Task Operator — 23× in this paper
• Accuracy — 22× in this paper · explained in 1 episode
• Steering — 14× in this paper · explained in 2 episodes
• Transformer — 10× in this paper · explained in 2 episodes
• Ablation — 8× in this paper · explained in 1 episode
• Benchmark — 5× in this paper · explained in 2 episodes
• Cosine Similarity — 4× in this paper · explained in 3 episodes
• In-Context Learning (ICL) — 4× in this paper · explained in 5 episodes
• Interpretability — 4× in this paper · explained in 15 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Function Vectors — 3× in this paper
• In-Context Vectors — 3× in this paper
• Robustness — 3× in this paper · explained in 5 episodes
• Ablation Studies — 2× in this paper · explained in 1 episode
• Chain-of-Thought (CoT) — 2× in this paper · explained in 4 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Pruning — 2× in this paper · explained in 4 episodes
• Activation Patching — 1× in this paper · explained in 2 episodes
• Activation Steering — 1× in this paper · explained in 4 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Aperture — 1× in this paper · explained in 1 episode
• Bayesian Inference — 1× in this paper · explained in 5 episodes
• Chain-of-Thought (CoT) Reasoning — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transformer Models — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Localizing Model Behavior with Path Patching
• The Llama 3 Herd of Models
• Refusal in LLMs is an Affine Function
• Qwen3 Technical Report

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