Generalization and Memorization along the Learning Trajectory of Neural Language Models: A Geometric Account of Categorization

arXiv:2609.32199 · cs.CL · Submitted 2026-09-26 · Read on arXiv

cs.CL

Submitted: 2026-09-26

Updated: 2026-09-26

Terminology

• Generalization — 44× in this paper · explained in 13 episodes
• Core — 32× in this paper · explained in 2 episodes
• Embeddings — 8× in this paper · explained in 2 episodes
• Transformer — 7× in this paper · explained in 2 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Generative AI — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Rethinking Memorization Measures and their Implications in Large Language Models
• Transformers perform adaptive partial pooling
• Scalable Extraction of Training Data from (Production) Language Models

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