Beyond the Rosetta Stone: Unification Forces in Generalization Dynamics

arXiv:2508.11017 · cs.CL, cs.AI · Submitted 2025-08-14 · Read on arXiv

cs.CL, cs.AI

Submitted: 2025-08-14

Updated: 2026-08-28

Project page: https://physics.allen-zhu.com

Terminology

• Generalization — 43× in this paper · explained in 13 episodes
• Accuracy — 39× in this paper · explained in 1 episode
• Cross-lingual Transfer — 17× in this paper · explained in 2 episodes
• Transformer — 6× in this paper · explained in 2 episodes
• Transformer Models — 4× in this paper · explained in 2 episodes
• Tokenization — 3× in this paper · explained in 2 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Core — 2× in this paper · explained in 2 episodes
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Hallucination — 2× in this paper · explained in 3 episodes
• Influence Functions — 2× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Data Augmentation — 1× in this paper · explained in 7 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Knowledge Graph — 1× in this paper · explained in 7 episodes
• Linear probe — 1× in this paper · explained in 2 episodes
• Procedural Knowledge — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Zero-Shot Transfer — 1× in this paper · explained in 4 episodes

Sources

• Language Models' Factuality Depends on the Language of Inquiry
• Scalable Influence and Fact Tracing for Large Language Model Pretraining
• Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models
• ECLeKTic: a Novel Challenge Set for Evaluation of Cross-Lingual Knowledge Transfer
• Language-Specific Latent Process Hinders Cross-Lingual Performance
• Tracing Multilingual Factual Knowledge Acquisition in Pretraining
• Gemma 2: Improving Open Language Models at a Practical Size
• Theoretical and Practical Perspectives on what Influence Functions Do
• Do Multilingual LLMs Think In English?
• Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models
• Hallucination is Inevitable: An Innate Limitation of Large 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