{"total":316,"rows":[{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716,"area":null},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2405.17398","title":"Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability","created":"2024-05-27","cited_by_count":347,"area":"wm"},{"id":"2502.02013","title":"Layer by Layer: Uncovering Hidden Representations in Language Models","created":"2025-02-04","cited_by_count":311,"area":null},{"id":"2405.14831","title":"HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models","created":"2024-05-23","cited_by_count":281,"area":"rag"},{"id":"2312.11970","title":"Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives","created":"2023-12-19","cited_by_count":257,"area":"agents"},{"id":"2403.17887","title":"The Unreasonable Ineffectiveness of the Deeper Layers","created":"2024-03-26","cited_by_count":226,"area":"lr"},{"id":"2405.14860","title":"Not All Language Model Features Are One-Dimensionally Linear","created":"2024-05-23","cited_by_count":212,"area":null},{"id":"2409.05907","title":"Programming Refusal with Conditional Activation Steering","created":"2024-09-06","cited_by_count":206,"area":"mechinterp"},{"id":"2310.20624","title":"LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B","created":"2023-10-31","cited_by_count":195,"area":"alignment"},{"id":"2605.29358","title":"Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet","created":"2026-05-28","cited_by_count":191,"area":"mechinterp"},{"id":"2503.08679","title":"Chain-of-Thought Reasoning In The Wild Is Not Always Faithful","created":"2025-03-11","cited_by_count":170,"area":"lr"},{"id":"2411.14499","title":"Understanding World or Predicting Future? A Comprehensive Survey of World Models","created":"2024-11-21","cited_by_count":166,"area":"wm"},{"id":"2402.16835","title":"Eight Methods to Evaluate Robust Unlearning in LLMs","created":"2024-02-26","cited_by_count":163,"area":"safety"},{"id":"2311.17842","title":"Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning","created":"2023-11-29","cited_by_count":161,"area":null},{"id":"2410.12877","title":"Improving Instruction-Following in Language Models through Activation Steering","created":"2024-10-15","cited_by_count":160,"area":"mechinterp"},{"id":"2406.01506","title":"The Geometry of Categorical and Hierarchical Concepts in Large Language Models","created":"2024-06-03","cited_by_count":159,"area":null},{"id":"2406.19384","title":"The Remarkable Robustness of LLMs: Stages of Inference?","created":"2024-06-27","cited_by_count":146,"area":null},{"id":"2406.07358","title":"AI Sandbagging: Language Models can Strategically Underperform on Evaluations","created":"2024-06-11","cited_by_count":145,"area":null},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"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":"2502.16681","title":"Are Sparse Autoencoders Useful? A Case Study in Sparse Probing","created":"2025-02-23","cited_by_count":115,"area":"mechinterp"},{"id":"2502.17420","title":"The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence","created":"2025-02-24","cited_by_count":115,"area":"alignment"},{"id":"2402.01801","title":"Large Language Models for Time Series: A Survey","created":"2024-02-02","cited_by_count":114,"area":null},{"id":"2401.12181","title":"Universal Neurons in GPT2 Language Models","created":"2024-01-22","cited_by_count":102,"area":"mechinterp"},{"id":"2310.10108","title":"On Generative Agents in Recommendation","created":"2023-10-16","cited_by_count":90,"area":"agents"},{"id":"2406.09170","title":"Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning","created":"2024-06-13","cited_by_count":88,"area":"lr"},{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"area":null},{"id":"2402.10877","title":"Robust agents learn causal world models","created":"2024-02-16","cited_by_count":81,"area":"wm"},{"id":"2503.03750","title":"The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems","created":"2025-03-05","cited_by_count":72,"area":"agents"},{"id":"2501.19309","title":"Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment","created":"2025-01-31","cited_by_count":59,"area":"alignment"},{"id":"2410.19750","title":"The Geometry of Concepts: Sparse Autoencoder Feature Structure","created":"2024-10-10","cited_by_count":52,"area":"mechinterp"},{"id":"2505.18235","title":"The Origins of Representation Manifolds in Large Language Models","created":"2025-05-23","cited_by_count":51,"area":"mechinterp"},{"id":"2501.00070","title":"ICLR: In-Context Learning of Representations","created":"2024-12-29","cited_by_count":50,"area":null},{"id":"2505.13898","title":"Do Language Models Use Their Depth Efficiently?","created":"2025-05-20","cited_by_count":50,"area":null},{"id":"2502.01563","title":"Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding","created":"2025-02-03","cited_by_count":47,"area":null},{"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":"2406.19501","title":"Monitoring Latent World States in Language Models with Propositional Probes","created":"2024-06-27","cited_by_count":43,"area":"wm"},{"id":"2502.15631","title":"The relationship between reasoning and performance in large language models--o3 (mini) thinks harder, not longer","created":"2025-02-21","cited_by_count":41,"area":"lr"},{"id":"2406.19370","title":"Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space","created":"2024-06-27","cited_by_count":35,"area":null},{"id":"2507.01786","title":"Probing and Steering Evaluation Awareness of Language Models","created":"2025-07-02","cited_by_count":35,"area":null},{"id":"2402.00795","title":"LLMs learn governing principles of dynamical systems, revealing an in-context neural scaling law","created":"2024-02-01","cited_by_count":32,"area":null},{"id":"2503.02080","title":"Linear Representations of Political Perspective Emerge in Large Language Models","created":"2025-03-03","cited_by_count":32,"area":"mechinterp"},{"id":"2402.18496","title":"Language Models Represent Beliefs of Self and Others","created":"2024-02-28","cited_by_count":31,"area":null},{"id":"2403.00025","title":"On the Challenges and Opportunities in Generative AI","created":"2024-02-28","cited_by_count":31,"area":null},{"id":"2511.05963","title":"Next-Latent Prediction Transformers Learn Compact World Models","created":"2025-11-08","cited_by_count":31,"area":"wm"},{"id":"2406.13948","title":"CityGPT: Empowering Urban Spatial Cognition of Large Language Models","created":"2024-06-20","cited_by_count":30,"area":"lr"},{"id":"2405.16229","title":"No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attacks","created":"2024-05-25","cited_by_count":29,"area":"alignment"},{"id":"2403.09037","title":"The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?","created":"2024-03-14","cited_by_count":26,"area":"mllm"},{"id":"2503.03730","title":"Towards Understanding Distilled Reasoning Models: A Representational Approach","created":"2025-03-05","cited_by_count":26,"area":"lr"},{"id":"2503.21411","title":"Exploring the Roles of Large Language Models in Reshaping Transportation Systems: A Survey, Framework, and Roadmap","created":"2025-03-27","cited_by_count":26,"area":null},{"id":"2408.13986","title":"AgentMove: A Large Language Model based Agentic Framework for Zero-shot Next Location Prediction","created":"2024-08-26","cited_by_count":25,"area":"agents"},{"id":"2409.09951","title":"Optimal ablation for interpretability","created":"2024-09-16","cited_by_count":25,"area":null},{"id":"2402.01749","title":"Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Models","created":"2024-01-30","cited_by_count":23,"area":null},{"id":"2512.07086","title":"ThinkTrap: Denial-of-Service Attacks against Black-box LLM Services via Infinite Thinking","created":"2025-12-08","cited_by_count":23,"area":"lr"},{"id":"2411.11114","title":"JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit","created":"2024-11-17","cited_by_count":22,"area":"safety"},{"id":"2506.06609","title":"Transferring Linear Features Across Language Models With Model Stitching","created":"2025-06-07","cited_by_count":21,"area":"mechinterp"},{"id":"2510.09782","title":"The Geometry of Reasoning: Flowing Logics in Representation Space","created":"2025-10-10","cited_by_count":21,"area":"lr"},{"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":"2405.04160","title":"A Causal Explainable Guardrails for Large Language Models","created":"2024-05-07","cited_by_count":18,"area":"safety"},{"id":"2407.05441","title":"Language Representations Can be What Recommenders Need: Findings and Potentials","created":"2024-07-07","cited_by_count":18,"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":"2404.01855","title":"Where to Move Next: Zero-shot Generalization of LLMs for Next POI Recommendation","created":"2024-04-02","cited_by_count":17,"area":null},{"id":"2408.03573","title":"AcTracer: Active Testing of Large Language Model via Multi-Stage Sampling","created":"2024-08-07","cited_by_count":17,"area":null},{"id":"2506.01622","title":"General agents contain world models","created":"2025-06-02","cited_by_count":17,"area":"wm"},{"id":"2602.02905","title":"FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights","created":"2026-02-02","cited_by_count":16,"area":"agents"},{"id":"2406.18722","title":"Towards Open-World Grasping with Large Vision-Language Models","created":"2024-06-26","cited_by_count":15,"area":"mllm"},{"id":"2409.03662","title":"The representation landscape of few-shot learning and fine-tuning in large language models","created":"2024-09-05","cited_by_count":15,"area":null},{"id":"2410.22330","title":"Vision-Language Models Create Cross-Modal Task Representations","created":"2024-10-29","cited_by_count":15,"area":"mllm"},{"id":"2501.00226","title":"Generative Emergent Communication: Large Language Model is a Collective World Model","created":"2024-12-31","cited_by_count":15,"area":"wm"},{"id":"2502.01540","title":"What is a Number, That a Large Language Model May Know It?","created":"2025-02-03","cited_by_count":15,"area":null},{"id":"2410.23501","title":"All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling","created":"2024-10-30","cited_by_count":14,"area":null},{"id":"2312.00819","title":"Large Language Models for Travel Behavior Prediction","created":"2023-11-30","cited_by_count":13,"area":null},{"id":"2502.18470","title":"Spatial-RAG: Spatial Retrieval Augmented Generation for Real-World Geospatial Reasoning Questions","created":"2025-02-04","cited_by_count":13,"area":"lr"},{"id":"2503.08980","title":"I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?","created":"2025-03-12","cited_by_count":13,"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":"2505.18651","title":"On the Emergence of Linear Analogies in Word Embeddings","created":"2025-05-24","cited_by_count":13,"area":null},{"id":"2506.08390","title":"On Reasoning Strength Planning in Large Reasoning Models","created":"2025-06-10","cited_by_count":13,"area":"lr"},{"id":"2512.18792","title":"The Dead Salmons of AI Interpretability","created":"2025-12-21","cited_by_count":12,"area":null},{"id":"2406.03345","title":"Feature contamination: Neural networks learn uncorrelated features and fail to generalize","created":"2024-06-05","cited_by_count":11,"area":null},{"id":"2406.19065","title":"STBench: Assessing the Ability of Large Language Models in Spatio-Temporal Analysis","created":"2024-06-27","cited_by_count":11,"area":null},{"id":"2602.15293","title":"The Information Geometry of Softmax: Probing and Steering","created":"2026-02-17","cited_by_count":11,"area":null},{"id":"2312.09634","title":"Vectorizing string entries for data processing on tables: when are larger language models better?","created":"2023-12-15","cited_by_count":10,"area":null},{"id":"2502.16690","title":"From Text to Space: Mapping Abstract Spatial Models in LLMs during a Grid-World Navigation Task","created":"2025-02-23","cited_by_count":10,"area":"agents"},{"id":"2503.13401","title":"Levels of Analysis for Large Language Models","created":"2025-03-17","cited_by_count":10,"area":null},{"id":"2504.02767","title":"How Deep Do Large Language Models Internalize Scientific Literature and Citation Practices?","created":"2025-04-03","cited_by_count":10,"area":null},{"id":"2507.20333","title":"The Blessing and Curse of Dimensionality in Safety Alignment","created":"2025-07-27","cited_by_count":10,"area":"alignment"},{"id":"2603.09972","title":"From Data Statistics to Feature Geometry: How Correlations Shape Superposition","created":"2026-03-10","cited_by_count":10,"area":"mechinterp"},{"id":"2408.12133","title":"Self-Supervised Representation Learning for Geospatial Objects: A Survey","created":"2024-08-22","cited_by_count":9,"area":null},{"id":"2404.18255","title":"PatentGPT: A Large Language Model for Intellectual Property","created":"2024-04-28","cited_by_count":8,"area":null},{"id":"2502.09297","title":"When Do Neural Networks Learn World Models?","created":"2025-02-13","cited_by_count":8,"area":"wm"},{"id":"2507.08017","title":"Mechanistic Indicators of Understanding in Large Language Models","created":"2025-07-07","cited_by_count":8,"area":null},{"id":"2507.21513","title":"What Does it Mean for a Neural Network to Learn a \"World Model\"?","created":"2025-07-29","cited_by_count":8,"area":"wm"},{"id":"2510.01025","title":"Hypothesis-Driven Feature Manifold Analysis in LLMs via Supervised Multi-Dimensional Scaling","created":"2025-10-01","cited_by_count":8,"area":null},{"id":"2512.16755","title":"CitySeeker: How Do VLMS Explore Embodied Urban Navigation With Implicit Human Needs?","created":"2025-12-18","cited_by_count":8,"area":"mllm"},{"id":"2603.06495","title":"COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics","created":"2026-03-06","cited_by_count":8,"area":"mechinterp"},{"id":"2607.12747","title":"Tracing Agentic Failure from the Flow of Success","created":"2026-07-14","cited_by_count":8,"area":"agents"},{"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":"2405.17420","title":"Survival of the Fittest Representation: A Case Study with Modular Addition","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2407.10020","title":"Causality extraction from medical text using Large Language Models (LLMs)","created":"2024-07-13","cited_by_count":7,"area":null}],"next_cursor":"100"}