{"total":36,"rows":[{"id":"2506.11613","title":"Model Organisms for Emergent Misalignment","created":"2025-06-13","cited_by_count":91,"area":null},{"id":"2406.12775","title":"Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop Queries","created":"2024-06-18","cited_by_count":78,"area":null},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"area":null},{"id":"2408.09503","title":"Out-of-distribution generalization via composition: a lens through induction heads in Transformers","created":"2024-08-18","cited_by_count":28,"area":null},{"id":"2509.21016","title":"RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs?","created":"2025-09-25","cited_by_count":23,"area":null},{"id":"2501.08537","title":"Complexity Control Facilitates Reasoning-Based Compositional Generalization in Transformers","created":"2025-01-15","cited_by_count":20,"area":null},{"id":"2410.08414","title":"Understanding the Interplay between Parametric and Contextual Knowledge for Large Language Models","created":"2024-10-10","cited_by_count":15,"area":null},{"id":"2509.21519","title":"Provable Scaling Laws of Feature Emergence from Learning Dynamics of Grokking","created":"2025-09-25","cited_by_count":15,"area":null},{"id":"2412.04614","title":"Extractive Structures Learned in Pretraining Enable Generalization on Finetuned Facts","created":"2024-12-05","cited_by_count":14,"area":null},{"id":"2504.01928","title":"Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure","created":"2025-04-02","cited_by_count":13,"area":null},{"id":"2504.13292","title":"Let Me Grok for You: Accelerating Grokking via Embedding Transfer from a Weaker Model","created":"2025-04-17","cited_by_count":13,"area":null},{"id":"2408.14915","title":"Can Transformers Do Enumerative Geometry?","created":"2024-08-27","cited_by_count":8,"area":null},{"id":"2510.01685","title":"How Do Language Models Compose Functions?","created":"2025-10-02","cited_by_count":8,"area":null},{"id":"2512.01970","title":"Atomic Skills are the Prerequisite: When Reinforcement Learning Synthesizes Compositional Reasoning, and When It Only Amplifies","created":"2025-12-01","cited_by_count":8,"area":null},{"id":"2605.13329","title":"Tracing Persona Vectors Through LLM Pretraining","created":"2026-05-13","cited_by_count":7,"area":null},{"id":"2509.09650","title":"All for One: LLMs Solve Mental Math at the Last Token With Information Transferred From Other Tokens","created":"2025-09-11","cited_by_count":5,"area":null},{"id":"2407.14055","title":"Quantum Hamiltonian Embedding of Images for Data Reuploading Classifiers","created":"2024-07-19","cited_by_count":4,"area":null},{"id":"2605.09724","title":"Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds","created":"2026-05-10","cited_by_count":4,"area":null},{"id":"2408.09818","title":"Liquid Fourier Latent Dynamics Networks for fast GPU-based numerical simulations in computational cardiology","created":"2024-08-19","cited_by_count":3,"area":null},{"id":"2505.20076","title":"ExPLAIND: Unifying Model, Data, and Training Attribution to Study Model Behavior","created":"2025-05-26","cited_by_count":3,"area":null},{"id":"2604.13082","title":"The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior","created":"2026-03-30","cited_by_count":3,"area":null},{"id":"2408.16667","title":"Iterative Graph Alignment","created":"2024-08-29","cited_by_count":2,"area":null},{"id":"2411.01375","title":"Learning with Hidden Factorial Structure","created":"2024-11-02","cited_by_count":2,"area":null},{"id":"2512.19879","title":"Fine-Tuned In-Context Learners for Efficient Adaptation","created":"2025-12-22","cited_by_count":2,"area":null},{"id":"2605.27078","title":"Two Speeds of Learning: A Representation-Readout Decomposition of Grokking and Double Descent","created":"2026-05-26","cited_by_count":2,"area":null},{"id":"2411.01030","title":"Birdie: Advancing State Space Models with Reward-Driven Objectives and Curricula","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2504.03162","title":"Beyond Progress Measures: Theoretical Insights into the Mechanism of Grokking","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2508.01763","title":"Reasoning Systems as Structured Processes: Foundations, Failures, and Formal Criteria","created":"2025-08-03","cited_by_count":1,"area":null},{"id":"2605.12394","title":"Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2502.03490","title":"Examining Two Hop Reasoning Through Information Content Scaling","created":"2025-02-05","cited_by_count":0,"area":null},{"id":"2507.18868","title":"A Neuroscience-Inspired Dual-Process Model of Compositional Generalization","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2508.00741","title":"Out-of-Context Abduction: LLMs Make Inferences About Procedural Data Leveraging Declarative Facts in Earlier Training Data","created":"2025-08-01","cited_by_count":0,"area":null},{"id":"2601.02931","title":"Memorization, Emergence, and Explaining Reversal Failures: A Controlled Study of Relational Semantics in LLMs","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2604.22951","title":"The Power of Power Law: Asymmetry Enables Compositional Reasoning","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2606.20737","title":"Repeated Shared Access Enables Grokking, but Edit Propagation Depends on an Addressable Memory","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2609.17594","title":"When the Gradient Sees Rank: Provable Necessity, Causal Recruitment, and Composition in Trained Matrix Memories","created":"2026-09-12","cited_by_count":0,"area":null}],"next_cursor":null}