LLMs Learn Better In-Context from Rules than from Examples

arXiv:2609.03213 · cs.CL · Submitted 2026-09-02 · Read on arXiv

cs.CL

Submitted: 2026-09-02

Updated: 2026-09-02

Code: https://github.com/tinlaboratory/rul

Terminology

• Accuracy — 39× in this paper · explained in 1 episode
• In-Context Learning — 21× in this paper · explained in 4 episodes
• Instruction Tuning — 8× in this paper · explained in 2 episodes
• Abstraction — 5× in this paper · explained in 1 episode
• Generalization — 5× in this paper · explained in 13 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes
• Thinking mode — 1× in this paper · explained in 2 episodes

Sources

• Transformers generalize differently from information stored in context vs in weights
• Gemma 3 Technical Report
• Efficient Memory Management for Large Language Model Serving with PagedAttention
• The broader spectrum of in-context learning
• Can LLMs Follow Simple Rules?
• Qwen2.5 Technical Report
• Qwen3 Technical Report
• Olmo 3
• Minimization of Boolean Complexity in In-Context Concept Learning
• Shared Lexical Task Representations Explain Behavioral Variability In LLMs
• Large Language Models can Learn Rules

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