{"total":123,"rows":[{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786,"area":null},{"id":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839,"area":"mechinterp"},{"id":"2210.13382","title":"Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task","created":"2022-10-24","cited_by_count":431,"area":null},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2309.00941","title":"Emergent Linear Representations in World Models of Self-Supervised Sequence Models","created":"2023-09-02","cited_by_count":319,"area":"wm"},{"id":"2205.15480","title":"Post-hoc Concept Bottleneck Models","created":"2022-05-31","cited_by_count":293,"area":null},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258,"area":null},{"id":"2307.15771","title":"The Hydra Effect: Emergent Self-repair in Language Model Computations","created":"2023-07-28","cited_by_count":156,"area":null},{"id":"2302.03025","title":"A Toy Model of Universality: Reverse Engineering How Networks Learn Group Operations","created":"2023-02-06","cited_by_count":144,"area":"mechinterp"},{"id":"2309.07311","title":"Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs","created":"2023-09-13","cited_by_count":124,"area":null},{"id":"2210.06313","title":"The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers","created":"2022-10-12","cited_by_count":122,"area":null},{"id":"2402.10376","title":"Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)","created":"2024-02-16","cited_by_count":119,"area":null},{"id":"2112.04417","title":"What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods","created":"2021-12-06","cited_by_count":98,"area":null},{"id":"2402.10877","title":"Robust agents learn causal world models","created":"2024-02-16","cited_by_count":81,"area":"wm"},{"id":"2403.03867","title":"On the Origins of Linear Representations in Large Language Models","created":"2024-03-06","cited_by_count":79,"area":null},{"id":"2306.09200","title":"ChessGPT: Bridging Policy Learning and Language Modeling","created":"2023-06-15","cited_by_count":75,"area":null},{"id":"2308.03685","title":"Learning Concise and Descriptive Attributes for Visual Recognition","created":"2023-08-07","cited_by_count":73,"area":"mllm"},{"id":"2308.07686","title":"Boosting Multi-modal Model Performance with Adaptive Gradient Modulation","created":"2023-08-15","cited_by_count":73,"area":null},{"id":"2204.01467","title":"On scientific understanding with artificial intelligence","created":"2022-04-04","cited_by_count":70,"area":null},{"id":"2306.01694","title":"Evaluating Language Models for Mathematics through Interactions","created":"2023-06-02","cited_by_count":70,"area":null},{"id":"2403.15498","title":"Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models","created":"2024-03-21","cited_by_count":62,"area":"wm"},{"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":"2408.00113","title":"Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models","created":"2024-07-31","cited_by_count":51,"area":"mechinterp"},{"id":"2301.11911","title":"Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees","created":"2023-01-27","cited_by_count":50,"area":null},{"id":"2306.06123","title":"Adversarial attacks and defenses in explainable artificial intelligence: A survey","created":"2023-06-06","cited_by_count":48,"area":null},{"id":"2310.16410","title":"Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero","created":"2023-10-25","cited_by_count":42,"area":null},{"id":"2402.02364","title":"Loss Landscape Degeneracy and Stagewise Development in Transformers","created":"2024-02-04","cited_by_count":40,"area":null},{"id":"2406.00877","title":"Evidence of Learned Look-Ahead in a Chess-Playing Neural Network","created":"2024-06-02","cited_by_count":34,"area":null},{"id":"2310.06301","title":"Dynamical versus Bayesian Phase Transitions in a Toy Model of Superposition","created":"2023-10-10","cited_by_count":29,"area":"mechinterp"},{"id":"2402.09236","title":"Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Models","created":"2024-02-14","cited_by_count":29,"area":null},{"id":"2304.09707","title":"Disentangling Neuron Representations with Concept Vectors","created":"2023-04-19","cited_by_count":28,"area":"mechinterp"},{"id":"2202.03482","title":"Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence","created":"2022-02-07","cited_by_count":25,"area":null},{"id":"2407.01067","title":"Human-like object concept representations emerge naturally in multimodal large language models","created":"2024-07-01","cited_by_count":25,"area":"mllm"},{"id":"2409.20553","title":"Maia-2: A Unified Model for Human-AI Alignment in Chess","created":"2024-09-30","cited_by_count":25,"area":null},{"id":"2502.07586","title":"We Can't Understand AI Using our Existing Vocabulary","created":"2025-02-11","cited_by_count":25,"area":null},{"id":"2503.07639","title":"Mixture of Experts Made Intrinsically Interpretable","created":"2025-03-05","cited_by_count":24,"area":"moe"},{"id":"2401.00788","title":"Astraios: Parameter-Efficient Instruction Tuning Code Large Language Models","created":"2024-01-01","cited_by_count":23,"area":null},{"id":"2402.05110","title":"Opening the AI black box: program synthesis via mechanistic interpretability","created":"2024-02-07","cited_by_count":20,"area":"mechinterp"},{"id":"2402.13914","title":"Position: Explain to Question not to Justify","created":"2024-02-21","cited_by_count":20,"area":null},{"id":"2407.15421","title":"Planning in a recurrent neural network that plays Sokoban","created":"2024-07-22","cited_by_count":18,"area":null},{"id":"2501.17186","title":"Complete Chess Games Enable LLM Become A Chess Master","created":"2025-01-26","cited_by_count":16,"area":null},{"id":"2308.09175","title":"Diversifying AI: Towards Creative Chess with AlphaZero","created":"2023-08-17","cited_by_count":15,"area":null},{"id":"2409.12272","title":"Mastering Chess with a Transformer Model","created":"2024-09-18","cited_by_count":15,"area":null},{"id":"2506.15872","title":"Hidden Breakthroughs in Language Model Training","created":"2025-06-18","cited_by_count":15,"area":null},{"id":"2501.17745","title":"Dynamics of Transient Structure in In-Context Linear Regression Transformers","created":"2025-01-29","cited_by_count":14,"area":null},{"id":"2212.08195","title":"Improving Chess Commentaries by Combining Language Models with Symbolic Reasoning Engines","created":"2022-12-15","cited_by_count":13,"area":"lr"},{"id":"2412.11867","title":"Transformers Use Causal World Models in Maze-Solving Tasks","created":"2024-12-16","cited_by_count":13,"area":"wm"},{"id":"2502.19805","title":"Implicit Search via Discrete Diffusion: A Study on Chess","created":"2025-02-27","cited_by_count":11,"area":"diffusion"},{"id":"2405.05066","title":"Designing Skill-Compatible AI: Methodologies and Frameworks in Chess","created":"2024-05-08","cited_by_count":10,"area":null},{"id":"2312.13839","title":"Q-SENN: Quantized Self-Explaining Neural Networks","created":"2023-12-21","cited_by_count":9,"area":null},{"id":"2211.14673","title":"Evaluation Beyond Task Performance: Analyzing Concepts in AlphaZero in Hex","created":"2022-11-26","cited_by_count":8,"area":null},{"id":"2403.14566","title":"A survey on Concept-based Approaches For Model Improvement","created":"2024-03-21","cited_by_count":8,"area":null},{"id":"2208.13776","title":"Attention-based Interpretable Regression of Gene Expression in Histology","created":"2022-08-29","cited_by_count":7,"area":null},{"id":"2210.05050","title":"Neurosymbolic Programming for Science","created":"2022-10-10","cited_by_count":7,"area":null},{"id":"2303.13166","title":"Take 5: Interpretable Image Classification with a Handful of Features","created":"2023-03-23","cited_by_count":7,"area":null},{"id":"2405.17088","title":"Phase Transitions in the Output Distribution of Large Language Models","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2410.03020","title":"On Logical Extrapolation for Mazes with Recurrent and Implicit Networks","created":"2024-10-03","cited_by_count":7,"area":null},{"id":"2412.11979","title":"AlphaZero Neural Scaling and Zipf's Law: a Tale of Board Games and Power Laws","created":"2024-12-16","cited_by_count":7,"area":null},{"id":"2507.21488","title":"Learning to Imitate with Less: Efficient Individual Behavior Modeling in Chess","created":"2025-07-29","cited_by_count":7,"area":null},{"id":"2209.11902","title":"Learning Chess With Language Models and Transformers","created":"2022-09-24","cited_by_count":6,"area":null},{"id":"2211.09937","title":"Explainability Via Causal Self-Talk","created":"2022-11-17","cited_by_count":6,"area":null},{"id":"2306.08593","title":"Heterogeneous Continual Learning","created":"2023-06-14","cited_by_count":6,"area":null},{"id":"2405.14602","title":"Controllable Continual Test-Time Adaptation","created":"2024-05-23","cited_by_count":6,"area":null},{"id":"2410.20811","title":"Bridging the Gap between Expert and Language Models: Concept-guided Chess Commentary Generation and Evaluation","created":"2024-10-28","cited_by_count":6,"area":null},{"id":"2502.06536","title":"Sample-efficient Learning of Concepts with Theoretical Guarantees: from Data to Concepts without Interventions","created":"2025-02-10","cited_by_count":6,"area":null},{"id":"2503.22720","title":"Why Representation Engineering Works: A Theoretical and Empirical Study in Vision-Language Models","created":"2025-03-25","cited_by_count":6,"area":"mllm"},{"id":"2605.19091","title":"Chessformer: A Unified Architecture for Chess Modeling","created":"2026-05-18","cited_by_count":6,"area":null},{"id":"2307.06913","title":"Uncovering Unique Concept Vectors through Latent Space Decomposition","created":"2023-07-13","cited_by_count":5,"area":null},{"id":"2312.00192","title":"Benchmarking and Enhancing Disentanglement in Concept-Residual Models","created":"2023-11-30","cited_by_count":5,"area":null},{"id":"2506.21590","title":"Representation Consistency for Accurate and Coherent LLM Answer Aggregation","created":"2025-06-18","cited_by_count":5,"area":"lr"},{"id":"2211.05500","title":"Reinforcement Learning in an Adaptable Chess Environment for Detecting Human-understandable Concepts","created":"2022-11-10","cited_by_count":4,"area":null},{"id":"2212.07877","title":"Manifestations of Xenophobia in AI Systems","created":"2022-12-15","cited_by_count":4,"area":null},{"id":"2311.14609","title":"Analysis of the expected $L_2$ error of an over-parametrized deep neural network estimate learned by gradient descent without regularization","created":"2023-11-24","cited_by_count":4,"area":null},{"id":"2401.16852","title":"Checkmating One, by Using Many: Combining Mixture of Experts with MCTS to Improve in Chess","created":"2024-01-30","cited_by_count":4,"area":"moe"},{"id":"2505.17323","title":"Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)","created":"2025-05-22","cited_by_count":4,"area":null},{"id":"2506.10138","title":"Path Channels and Plan Extension Kernels: a Mechanistic Description of Planning in a Sokoban RNN","created":"2025-06-11","cited_by_count":4,"area":"deeprl"},{"id":"2601.07524","title":"Stagewise Reinforcement Learning and the Geometry of the Regret Landscape","created":"2026-01-12","cited_by_count":4,"area":"deeprl"},{"id":"2204.07531","title":"Understanding Game-Playing Agents with Natural Language Annotations","created":"2022-04-15","cited_by_count":3,"area":null},{"id":"2206.09046","title":"Beyond Rewards: a Hierarchical Perspective on Offline Multiagent Behavioral Analysis","created":"2022-06-17","cited_by_count":3,"area":null},{"id":"2208.02187","title":"On the independence between phenomenal consciousness and computational intelligence","created":"2022-08-03","cited_by_count":3,"area":null},{"id":"2303.09154","title":"Bayesian Generalization Error in Linear Neural Networks with Concept Bottleneck Structure and Multitask Formulation","created":"2023-03-16","cited_by_count":3,"area":null},{"id":"2309.09702","title":"Information based explanation methods for deep learning agents -- with applications on large open-source chess models","created":"2023-09-18","cited_by_count":3,"area":null},{"id":"2310.03149","title":"Attributing Learned Concepts in Neural Networks to Training Data","created":"2023-10-04","cited_by_count":3,"area":null},{"id":"2410.14890","title":"Reasoning, Memorization, and Fine-Tuning Language Models for Non-Cooperative Games","created":"2024-10-18","cited_by_count":3,"area":"lr"},{"id":"2503.08636","title":"Birds look like cars: Adversarial analysis of intrinsically interpretable deep learning","created":"2025-03-11","cited_by_count":3,"area":null},{"id":"2508.20040","title":"Model Science: getting serious about verification, explanation and control of AI systems","created":"2025-08-27","cited_by_count":3,"area":null},{"id":"2301.01819","title":"A Model for Intelligible Interaction Between Agents That Predict and Explain","created":"2023-01-04","cited_by_count":2,"area":null},{"id":"2312.05092","title":"INSPECT: Intrinsic and Systematic Probing Evaluation for Code Transformers","created":"2023-12-08","cited_by_count":2,"area":null},{"id":"2406.04028","title":"Contrastive Sparse Autoencoders for Interpreting Planning of Chess-Playing Agents","created":"2024-06-06","cited_by_count":2,"area":"mechinterp"},{"id":"2411.10019","title":"Towards Utilising a Range of Neural Activations for Comprehending Representational Associations","created":"2024-11-15","cited_by_count":2,"area":null},{"id":"2502.14998","title":"Generative Modeling of Individual Behavior at Scale","created":"2025-02-20","cited_by_count":2,"area":null},{"id":"2502.20130","title":"QPM: Discrete Optimization for Globally Interpretable Image Classification","created":"2025-02-27","cited_by_count":2,"area":null},{"id":"2503.22478","title":"Almost Bayesian: The Fractal Dynamics of Stochastic Gradient Descent","created":"2025-03-28","cited_by_count":2,"area":null},{"id":"2504.05393","title":"Interactive Explanations for Reinforcement-Learning Agents","created":"2025-04-07","cited_by_count":2,"area":"deeprl"},{"id":"2604.10158","title":"Tracing the Thought of a Grandmaster-level Chess-Playing Transformer","created":"2026-04-11","cited_by_count":2,"area":null},{"id":"2608.06741","title":"Solver-Guided Reasoning for Mixed-Equilibrium Strategies","created":"2026-08-07","cited_by_count":2,"area":"lr"},{"id":"2201.06274","title":"Detecting danger in gridworlds using Gromov's Link Condition","created":"2022-01-17","cited_by_count":1,"area":null},{"id":"2307.12601","title":"Concept backpropagation: An Explainable AI approach for visualising learned concepts in neural network models","created":"2023-07-24","cited_by_count":1,"area":null},{"id":"2312.03762","title":"Colour versus Shape Goal Misgeneralization in Reinforcement Learning: A Case Study","created":"2023-12-05","cited_by_count":1,"area":null},{"id":"2403.09206","title":"Upper Bound of Bayesian Generalization Error in Partial Concept Bottleneck Model (CBM): Partial CBM outperforms naive CBM","created":"2024-03-14","cited_by_count":1,"area":null}],"next_cursor":"100"}