{"total":79,"rows":[{"id":"2407.02646","title":"A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models","created":"2024-07-02","cited_by_count":118,"area":"mechinterp"},{"id":"2506.11613","title":"Model Organisms for Emergent Misalignment","created":"2025-06-13","cited_by_count":91,"area":null},{"id":"2412.16075","title":"Formal Mathematical Reasoning: A New Frontier in AI","created":"2024-12-20","cited_by_count":81,"area":"lr"},{"id":"2507.06203","title":"A Survey on Latent Reasoning","created":"2025-07-08","cited_by_count":81,"area":"lr"},{"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":"2505.12514","title":"Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought","created":"2025-05-18","cited_by_count":77,"area":"lr"},{"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":"2411.13504","title":"Disentangling Memory and Reasoning Ability in Large Language Models","created":"2024-11-20","cited_by_count":44,"area":"lr"},{"id":"2509.02350","title":"Implicit Reasoning in Large Language Models: A Comprehensive Survey","created":"2025-09-02","cited_by_count":43,"area":"lr"},{"id":"2411.12580","title":"Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models","created":"2024-11-19","cited_by_count":41,"area":"lr"},{"id":"2505.13775","title":"Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate Tokens","created":"2025-05-19","cited_by_count":41,"area":"lr"},{"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":"2411.16679","title":"Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts?","created":"2024-11-25","cited_by_count":28,"area":"lr"},{"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":"2503.23084","title":"The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction","created":"2025-03-29","cited_by_count":21,"area":"lr"},{"id":"2501.08537","title":"Complexity Control Facilitates Reasoning-Based Compositional Generalization in Transformers","created":"2025-01-15","cited_by_count":20,"area":null},{"id":"2502.13913","title":"How Do LLMs Perform Two-Hop Reasoning in Context?","created":"2025-02-19","cited_by_count":20,"area":"lr"},{"id":"2410.09542","title":"MIRAGE: Evaluating and Explaining Inductive Reasoning Process in Language Models","created":"2024-10-12","cited_by_count":17,"area":"lr"},{"id":"2411.16353","title":"Lessons from Studying Two-Hop Latent Reasoning","created":"2024-11-25","cited_by_count":17,"area":"lr"},{"id":"2411.15862","title":"Do LLMs Really Think Step-by-step In Implicit Reasoning?","created":"2024-11-24","cited_by_count":16,"area":"lr"},{"id":"2405.15302","title":"Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanism","created":"2024-05-24","cited_by_count":15,"area":"lr"},{"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":"2504.20752","title":"Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers","created":"2025-04-29","cited_by_count":12,"area":"lr"},{"id":"2602.00449","title":"Do Latent-CoT Models Think Step-by-Step? A Mechanistic Study on Sequential Reasoning Tasks","created":"2026-01-31","cited_by_count":12,"area":"lr"},{"id":"2512.14693","title":"Universal Reasoning Model","created":"2025-12-16","cited_by_count":11,"area":"lr"},{"id":"2502.07087","title":"Evaluating the Systematic Reasoning Abilities of Large Language Models through Graph Coloring","created":"2025-02-10","cited_by_count":10,"area":"lr"},{"id":"2506.21551","title":"Grokking in LLM Pretraining? Monitor Memorization-to-Generalization without Test","created":"2025-06-26","cited_by_count":10,"area":"moe"},{"id":"2509.07339","title":"Performative Thinking? The Brittle Correlation Between CoT Length and Problem Complexity","created":"2025-09-09","cited_by_count":9,"area":"lr"},{"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":"2607.16051","title":"Loop the Loopies!","created":"2026-07-17","cited_by_count":8,"area":"moe"},{"id":"2504.04215","title":"Towards Understanding and Improving Refusal in Compressed Models via Mechanistic Interpretability","created":"2025-04-05","cited_by_count":7,"area":"mechinterp"},{"id":"2506.15732","title":"Can LLMs Reconcile Knowledge Conflicts in Counterfactual Reasoning","created":"2025-06-15","cited_by_count":7,"area":"lr"},{"id":"2605.13329","title":"Tracing Persona Vectors Through LLM Pretraining","created":"2026-05-13","cited_by_count":7,"area":null},{"id":"2505.00808","title":"A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.i","created":"2025-05-01","cited_by_count":6,"area":"mechinterp"},{"id":"2409.09281","title":"Language Models \"Grok\" to Copy","created":"2024-09-14","cited_by_count":5,"area":"rag"},{"id":"2409.10840","title":"Implicit Reasoning in Deep Time Series Forecasting","created":"2024-09-17","cited_by_count":5,"area":"lr"},{"id":"2502.07813","title":"CryptoX : Compositional Reasoning Evaluation of Large Language Models","created":"2025-02-08","cited_by_count":5,"area":"lr"},{"id":"2503.04796","title":"Optimizing Multi-Hop Document Retrieval Through Intermediate Representations","created":"2025-03-02","cited_by_count":5,"area":"rag"},{"id":"2507.04782","title":"Reason to Rote: Rethinking Memorization in Reasoning","created":"2025-07-07","cited_by_count":5,"area":"lr"},{"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":"2504.00472","title":"Memorizing is Not Enough: Deep Knowledge Injection Through Reasoning","created":"2025-04-01","cited_by_count":4,"area":"lr"},{"id":"2506.09099","title":"Too Big to Think: Capacity, Memorization, and Generalization in Pre-Trained Transformers","created":"2025-06-10","cited_by_count":4,"area":"lr"},{"id":"2512.02004","title":"AlignSAE: Concept-Aligned Sparse Autoencoders","created":"2025-12-01","cited_by_count":4,"area":"mechinterp"},{"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":"2607.00341","title":"DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning","created":"2026-07-01","cited_by_count":4,"area":"lr"},{"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":"2502.06037","title":"Investigating Compositional Reasoning in Time Series Foundation Models","created":"2025-02-09","cited_by_count":3,"area":"lr"},{"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":"2509.17514","title":"Achilles' Heel of Mamba: Essential difficulties of the Mamba architecture demonstrated by synthetic data","created":"2025-09-22","cited_by_count":3,"area":"ssm"},{"id":"2510.22099","title":"Generalization or Memorization: Dynamic Decoding for Mode Steering","created":"2025-10-25","cited_by_count":3,"area":"mechinterp"},{"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":"2601.17593","title":"From Chains to DAGs: Probing the Graph Structure of Reasoning in LLMs","created":"2026-01-24","cited_by_count":2,"area":"lr"},{"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":"2409.19745","title":"PEAR: Position-Embedding-Agnostic Attention Re-weighting Enhances Retrieval-Augmented Generation with Zero Inference Overhead","created":"2024-09-29","cited_by_count":1,"area":"rag"},{"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":"2601.14270","title":"Opening the Black Box: A Survey on the Mechanisms of Multi-Step Reasoning in Large Language Models","created":"2026-01-02","cited_by_count":1,"area":"lr"},{"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":"2510.25791","title":"The Kinetics of Reasoning: How Chain-of-Thought Shapes Learning in Transformers?","created":"2025-10-28","cited_by_count":0,"area":"lr"},{"id":"2512.14427","title":"Effect of Document Packing on the Latent Multi-Hop Reasoning Capabilities of Large Language Models","created":"2025-12-16","cited_by_count":0,"area":"lr"},{"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},{"id":"2609.19878","title":"Uni-LaDiR: Latent Diffusion Unifies Multimodal Reasoning","created":"2026-09-17","cited_by_count":0,"area":"lr"}],"next_cursor":null}