{"total":62,"rows":[{"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":"2507.06952","title":"What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models","created":"2025-07-09","cited_by_count":47,"area":"wm"},{"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":"2503.02854","title":"(How) Do Language Models Track State?","created":"2025-03-04","cited_by_count":34,"area":null},{"id":"2406.00244","title":"Controlling Large Language Model Agents with Entropic Activation Steering","created":"2024-06-01","cited_by_count":29,"area":"agents"},{"id":"2503.07639","title":"Mixture of Experts Made Intrinsically Interpretable","created":"2025-03-05","cited_by_count":24,"area":"moe"},{"id":"2504.19483","title":"Improving Reasoning Performance in Large Language Models via Representation Engineering","created":"2025-04-28","cited_by_count":23,"area":"lr"},{"id":"2406.16033","title":"Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models","created":"2024-06-23","cited_by_count":22,"area":"mechinterp"},{"id":"2406.11741","title":"Transcendence: Generative Models Can Outperform The Experts That Train Them","created":"2024-06-17","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":"2506.01622","title":"General agents contain world models","created":"2025-06-02","cited_by_count":17,"area":"wm"},{"id":"2412.11867","title":"Transformers Use Causal World Models in Maze-Solving Tasks","created":"2024-12-16","cited_by_count":13,"area":"wm"},{"id":"2410.03893","title":"Human-aligned Chess with a Bit of Search","created":"2024-10-04","cited_by_count":11,"area":null},{"id":"2502.19805","title":"Implicit Search via Discrete Diffusion: A Study on Chess","created":"2025-02-27","cited_by_count":11,"area":"diffusion"},{"id":"2503.04421","title":"Revisiting the Othello World Model Hypothesis","created":"2025-03-06","cited_by_count":11,"area":"wm"},{"id":"2503.13401","title":"Levels of Analysis for Large Language Models","created":"2025-03-17","cited_by_count":10,"area":null},{"id":"2505.14925","title":"Too Long, Didn't Model: Decomposing LLM Long-Context Understanding With Novels","created":"2025-05-20","cited_by_count":9,"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":"2506.02996","title":"Linear Spatial World Models Emerge in Large Language Models","created":"2025-06-03","cited_by_count":6,"area":"wm"},{"id":"2512.21577","title":"A Unified Definition of Hallucination: It's The World Model, Stupid!","created":"2025-12-25","cited_by_count":6,"area":"wm"},{"id":"2605.19091","title":"Chessformer: A Unified Architecture for Chess Modeling","created":"2026-05-18","cited_by_count":6,"area":null},{"id":"2605.30233","title":"Do Language Models Track Entities Across State Changes?","created":"2026-05-28","cited_by_count":6,"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":"2512.03400","title":"Better World Models Can Lead to Better Post-Training Performance","created":"2025-12-03","cited_by_count":4,"area":"wm"},{"id":"2602.23164","title":"MetaOthello: A Controlled Study of Multiple World Models in Transformers","created":"2026-02-26","cited_by_count":4,"area":"wm"},{"id":"2502.14171","title":"Enhancing Conversational Agents with Theory of Mind: Aligning Beliefs, Desires, and Intentions for Human-Like Interaction","created":"2025-02-20","cited_by_count":3,"area":"agents"},{"id":"2511.12239","title":"Beyond World Models: Rethinking Understanding in AI Models","created":"2025-11-15","cited_by_count":3,"area":"wm"},{"id":"2506.19095","title":"Baba is LLM: Reasoning in a Game with Dynamic Rules","created":"2025-06-23","cited_by_count":2,"area":"lr"},{"id":"2509.17280","title":"From Prediction to Understanding: Will AI Foundation Models Transform Brain Science?","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2606.29315","title":"Hierarchical Experimentalist Agents","created":"2026-06-28","cited_by_count":2,"area":"agents"},{"id":"2506.19079","title":"Reading Smiles: Proxy Bias in Foundation Models for Facial Emotion Recognition","created":"2025-06-23","cited_by_count":1,"area":"mllm"},{"id":"2512.23722","title":"Emergent World Beliefs: Exploring Transformers in Stochastic Games","created":"2025-12-18","cited_by_count":1,"area":"lr"},{"id":"2602.04447","title":"Mixture of Masters: Sparse Chess Language Models with Player Routing","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2602.05903","title":"Verification of the Implicit World Model in a Generative Model via Adversarial Sequences","created":"2026-02-05","cited_by_count":1,"area":"wm"},{"id":"2603.16689","title":"Predictive Statistics Shape Emergent World Representations of Grid Walkers","created":"2026-03-17","cited_by_count":1,"area":"wm"},{"id":"2605.12809","title":"Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.30100","title":"Chess-World-Model: A 10M-Game Benchmark for Exact State Tracking from Chess Move Sequences","created":"2026-05-28","cited_by_count":1,"area":"wm"},{"id":"2607.05188","title":"Latent Programming Horizons in Coding Agents","created":"2026-07-06","cited_by_count":1,"area":"agents"},{"id":"2609.14011","title":"Convergent Emergence of In-Context Learning Across Modalities","created":"2026-09-12","cited_by_count":1,"area":null},{"id":"2505.21552","title":"Understanding the learned look-ahead behavior of chess neural networks","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2507.14520","title":"What if Othello-Playing Language Models Could See?","created":"2025-07-19","cited_by_count":0,"area":null},{"id":"2510.27009","title":"Causal Masking on Spatial Data: An Information-Theoretic Case for Learning Spatial Datasets with Unimodal Language Models","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2511.13021","title":"PragWorld: A Benchmark Evaluating LLMs' Local World Model under Minimal Linguistic Alterations and Conversational Dynamics","created":"2025-11-17","cited_by_count":0,"area":"wm"},{"id":"2602.01716","title":"Mechanistic Indicators of Steering Effectiveness in Large Language Models","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2603.14087","title":"Understanding the Emergence of Seemingly Useless Features in Next-Token Predictors","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2603.29761","title":"Tracking vs. Deciding: The Dual-Capability Bottleneck in Searchless Chess Transformers","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2605.04899","title":"A geometric relation of the error introduced by sampling a language model's output distribution to its internal state","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.23972","title":"Why We Need World Models for AGI: Where LLMs Fail and How World Models May Outperform","created":"2026-05-13","cited_by_count":0,"area":"wm"},{"id":"2605.27767","title":"UniMaia: Steering Chess Policies with Language for Human-like Play","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.03685","title":"A Close Look At World Model Recovery In Supervised Fine-Tuned LLM Planners","created":"2026-06-02","cited_by_count":0,"area":"wm"},{"id":"2606.28127","title":"From Tokens to States: LLMs as a Special Case of World Models and the Continuous Path Beyond","created":"2026-06-26","cited_by_count":0,"area":"wm"},{"id":"2607.10248","title":"One mechanism for many mental spaces: a shared router over a value slot in language models","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2607.11953","title":"When Does Reward Teach State? A Hidden-Automaton Instrument and a Group-Language Warning Signal","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2608.30751","title":"Autoregressive Mosaics: Probing 2D Spatial Reasoning in Text-Only Language Models","created":"2026-08-31","cited_by_count":0,"area":"lr"},{"id":"2609.18286","title":"What Counts as Strategic Reasoning? A Systematic Mapping of Chess Research on Humans, Engines, and Language Models","created":"2026-09-16","cited_by_count":0,"area":"lr"},{"id":"2609.21748","title":"World Modeling in Transformers","created":"2026-09-18","cited_by_count":0,"area":"wm"},{"id":"2609.23917","title":"Increasing Skill Level Recruits Deeper Attention Layers in a Frozen Chess Transformer","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.24352","title":"Few-Shot Demonstrations Elicit the Use of In-Context World Representations in LLMs","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.30936","title":"Self-Play Search Distillation for Large Language Model Reasoning","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.38718","title":"MetaSteer: Context-Conditioned, nonlinear Steering via Attention-Projection Adaptation","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00416","title":"Benchmarking Prompt Optimization of Large Language Models With Chess","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.12847","title":"When Generative Models Act as Simulators","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}