{"total":431,"rows":[{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439,"area":"agents"},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302,"area":null},{"id":"2308.10248","title":"Steering Language Models With Activation Engineering","created":"2023-08-20","cited_by_count":922,"area":"mechinterp"},{"id":"2307.05782","title":"Large Language Models","created":"2023-07-11","cited_by_count":780,"area":null},{"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":"2310.06824","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","created":"2023-10-10","cited_by_count":712,"area":null},{"id":"2303.08112","title":"Eliciting Latent Predictions from Transformers with the Tuned Lens","created":"2023-03-14","cited_by_count":623,"area":"mechinterp"},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2309.16042","title":"Towards Best Practices of Activation Patching in Language Models: Metrics and Methods","created":"2023-09-27","cited_by_count":359,"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":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334,"area":null},{"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":"2310.02207","title":"Language Models Represent Space and Time","created":"2023-10-03","cited_by_count":316,"area":null},{"id":"2402.10588","title":"Do Llamas Work in English? On the Latent Language of Multilingual Transformers","created":"2024-02-16","cited_by_count":281,"area":null},{"id":"2307.02477","title":"Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks","created":"2023-07-05","cited_by_count":246,"area":"lr"},{"id":"2311.06668","title":"In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering","created":"2023-11-11","cited_by_count":245,"area":null},{"id":"2405.14860","title":"Not All Language Model Features Are One-Dimensionally Linear","created":"2024-05-23","cited_by_count":212,"area":null},{"id":"2305.14909","title":"Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning","created":"2023-05-24","cited_by_count":207,"area":"wm"},{"id":"2305.00586","title":"How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model","created":"2023-04-30","cited_by_count":202,"area":null},{"id":"2605.29358","title":"Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet","created":"2026-05-28","cited_by_count":191,"area":"mechinterp"},{"id":"2401.01967","title":"A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity","created":"2024-01-03","cited_by_count":185,"area":"alignment"},{"id":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163,"area":null},{"id":"2409.14507","title":"A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders","created":"2024-09-22","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":"2402.14811","title":"Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking","created":"2024-02-22","cited_by_count":149,"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":"2407.12404","title":"Analyzing the Generalization and Reliability of Steering Vectors","created":"2024-07-17","cited_by_count":143,"area":"mechinterp"},{"id":"2303.13506","title":"The Quantization Model of Neural Scaling","created":"2023-03-23","cited_by_count":138,"area":null},{"id":"2408.10205","title":"KAN 2.0: Kolmogorov-Arnold Networks Meet Science","created":"2024-08-19","cited_by_count":118,"area":null},{"id":"2311.12786","title":"Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks","created":"2023-11-21","cited_by_count":115,"area":null},{"id":"2406.03689","title":"Evaluating the World Model Implicit in a Generative Model","created":"2024-06-06","cited_by_count":113,"area":"wm"},{"id":"2404.02039","title":"A Survey on Large Language Model-Based Game Agents","created":"2024-04-02","cited_by_count":112,"area":"agents"},{"id":"2309.02390","title":"Explaining grokking through circuit efficiency","created":"2023-09-05","cited_by_count":111,"area":null},{"id":"2310.17191","title":"How do Language Models Bind Entities in Context?","created":"2023-10-26","cited_by_count":108,"area":null},{"id":"2402.12275","title":"WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment","created":"2024-02-19","cited_by_count":107,"area":"wm"},{"id":"2410.02762","title":"Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations","created":"2024-10-03","cited_by_count":104,"area":"mllm"},{"id":"2305.16130","title":"Language Models Implement Simple Word2Vec-style Vector Arithmetic","created":"2023-05-25","cited_by_count":98,"area":null},{"id":"2410.21272","title":"Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics","created":"2024-10-28","cited_by_count":97,"area":"lr"},{"id":"2402.18659","title":"Large Language Models and Games: A Survey and Roadmap","created":"2024-02-28","cited_by_count":93,"area":null},{"id":"2402.17811","title":"TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space","created":"2024-02-27","cited_by_count":91,"area":null},{"id":"2601.07372","title":"Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models","created":"2026-01-12","cited_by_count":86,"area":"moe"},{"id":"2402.10877","title":"Robust agents learn causal world models","created":"2024-02-16","cited_by_count":81,"area":"wm"},{"id":"2405.15943","title":"Transformers represent belief state geometry in their residual stream","created":"2024-05-24","cited_by_count":77,"area":null},{"id":"2404.01650","title":"Test-Time Model Adaptation with Only Forward Passes","created":"2024-04-02","cited_by_count":74,"area":null},{"id":"2303.07103","title":"Could a Large Language Model be Conscious?","created":"2023-03-04","cited_by_count":73,"area":null},{"id":"2304.00612","title":"Eight Things to Know about Large Language Models","created":"2023-04-02","cited_by_count":73,"area":null},{"id":"2503.18968","title":"MedAgent-Pro: Towards Evidence-based Multi-modal Medical Diagnosis via Reasoning Agentic Workflow","created":"2025-03-21","cited_by_count":73,"area":"lr"},{"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":"2308.01399","title":"Learning to Model the World with Language","created":"2023-07-31","cited_by_count":68,"area":null},{"id":"2402.16153","title":"ChatMusician: Understanding and Generating Music Intrinsically with LLM","created":"2024-02-25","cited_by_count":68,"area":null},{"id":"2308.09067","title":"Contrasting Linguistic Patterns in Human and LLM-Generated News Text","created":"2023-08-17","cited_by_count":62,"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":"2506.10805","title":"Detecting High-Stakes Interactions with Activation Probes","created":"2025-06-12","cited_by_count":53,"area":null},{"id":"2410.19750","title":"The Geometry of Concepts: Sparse Autoencoder Feature Structure","created":"2024-10-10","cited_by_count":52,"area":"mechinterp"},{"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":"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":"2308.01544","title":"Multimodal Neurons in Pretrained Text-Only Transformers","created":"2023-08-03","cited_by_count":49,"area":null},{"id":"2401.12874","title":"From Understanding to Utilization: A Survey on Explainability for Large Language Models","created":"2024-01-23","cited_by_count":48,"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":"2310.04276","title":"From task structures to world models: What do LLMs know?","created":"2023-10-06","cited_by_count":46,"area":"wm"},{"id":"2305.02363","title":"Entity Tracking in Language Models","created":"2023-05-03","cited_by_count":44,"area":null},{"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":"2501.09781","title":"VideoWorld: Exploring Knowledge Learning from Unlabeled Videos","created":"2025-01-16","cited_by_count":43,"area":null},{"id":"2402.02651","title":"Vision-Language Models Provide Promptable Representations for Reinforcement Learning","created":"2024-02-05","cited_by_count":41,"area":"mllm"},{"id":"2406.19215","title":"SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation","created":"2024-06-27","cited_by_count":40,"area":"rag"},{"id":"2304.01481","title":"The Vector Grounding Problem","created":"2023-04-04","cited_by_count":39,"area":null},{"id":"2410.06331","title":"Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing","created":"2024-10-08","cited_by_count":37,"area":null},{"id":"2306.00966","title":"The Hidden Language of Diffusion Models","created":"2023-06-01","cited_by_count":34,"area":"diffusion"},{"id":"2307.03637","title":"Discovering Variable Binding Circuitry with Desiderata","created":"2023-07-07","cited_by_count":34,"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":"2503.02854","title":"(How) Do Language Models Track State?","created":"2025-03-04","cited_by_count":34,"area":null},{"id":"2308.08090","title":"Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation","created":"2023-08-16","cited_by_count":33,"area":"safety"},{"id":"2311.13594","title":"Labeling Neural Representations with Inverse Recognition","created":"2023-11-22","cited_by_count":32,"area":null},{"id":"2411.04430","title":"Towards Unifying Interpretability and Control: Evaluation via Intervention","created":"2024-11-07","cited_by_count":32,"area":"mechinterp"},{"id":"2401.14953","title":"Learning Universal Predictors","created":"2024-01-26","cited_by_count":31,"area":null},{"id":"2402.18496","title":"Language Models Represent Beliefs of Self and Others","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":"2305.11169","title":"Emergent Representations of Program Semantics in Language Models Trained on Programs","created":"2023-05-18","cited_by_count":30,"area":"wm"},{"id":"2306.05720","title":"Beyond Surface Statistics: Scene Representations in a Latent Diffusion Model","created":"2023-06-09","cited_by_count":30,"area":"diffusion"},{"id":"2311.09433","title":"Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment","created":"2023-11-15","cited_by_count":30,"area":"safety"},{"id":"2405.21030","title":"Standards for Belief Representations in LLMs","created":"2024-05-31","cited_by_count":30,"area":null},{"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":"2402.12201","title":"Dictionary Learning Improves Patch-Free Circuit Discovery in Mechanistic Interpretability: A Case Study on Othello-GPT","created":"2024-02-19","cited_by_count":29,"area":"mechinterp"},{"id":"2409.05448","title":"Representational Analysis of Binding in Language Models","created":"2024-09-09","cited_by_count":28,"area":null},{"id":"2402.15690","title":"Foot In The Door: Understanding Large Language Model Jailbreaking via Cognitive Psychology","created":"2024-02-24","cited_by_count":27,"area":"safety"},{"id":"2410.00153","title":"Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution","created":"2024-09-30","cited_by_count":27,"area":null},{"id":"2410.14516","title":"Do LLMs \"know\" internally when they follow instructions?","created":"2024-10-18","cited_by_count":26,"area":null},{"id":"2502.13092","title":"Text2World: Benchmarking Large Language Models for Symbolic World Model Generation","created":"2025-02-18","cited_by_count":26,"area":"wm"},{"id":"2409.09951","title":"Optimal ablation for interpretability","created":"2024-09-16","cited_by_count":25,"area":null},{"id":"2505.24535","title":"Beyond Linear Steering: Unified Multi-Attribute Control for Language Models","created":"2025-05-30","cited_by_count":25,"area":null},{"id":"2408.01416","title":"The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis","created":"2024-08-02","cited_by_count":24,"area":"mechinterp"},{"id":"2510.07358","title":"Encode, Think, Decode: Scaling test-time reasoning with recursive latent thoughts","created":"2025-10-08","cited_by_count":24,"area":"lr"},{"id":"2409.10053","title":"Householder Pseudo-Rotation: A Novel Approach to Activation Editing in LLMs with Direction-Magnitude Perspective","created":"2024-09-16","cited_by_count":23,"area":"mechinterp"},{"id":"2311.12997","title":"Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks","created":"2023-11-21","cited_by_count":22,"area":null},{"id":"2402.10688","title":"Towards Uncovering How Large Language Model Works: An Explainability Perspective","created":"2024-02-16","cited_by_count":22,"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":"2407.08734","title":"Transformer Circuit Faithfulness Metrics are not Robust","created":"2024-07-11","cited_by_count":22,"area":"mechinterp"},{"id":"2412.01800","title":"PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videos","created":"2024-12-02","cited_by_count":22,"area":null},{"id":"2502.07827","title":"Implicit Language Models are RNNs: Balancing Parallelization and Expressivity","created":"2025-02-10","cited_by_count":22,"area":"lr"}],"next_cursor":"100"}