{"total":119,"rows":[{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807,"area":"lr"},{"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":"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":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382,"area":null},{"id":"2310.02207","title":"Language Models Represent Space and Time","created":"2023-10-03","cited_by_count":316,"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":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221,"area":null},{"id":"2302.02662","title":"Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning","created":"2023-02-06","cited_by_count":195,"area":null},{"id":"2304.00740","title":"Inspecting and Editing Knowledge Representations in Language Models","created":"2023-04-03","cited_by_count":141,"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":"2406.14852","title":"Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models","created":"2024-06-21","cited_by_count":113,"area":"lr"},{"id":"2405.08366","title":"Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control","created":"2024-05-14","cited_by_count":86,"area":"mechinterp"},{"id":"2402.10877","title":"Robust agents learn causal world models","created":"2024-02-16","cited_by_count":81,"area":"wm"},{"id":"2208.02957","title":"Meaning without reference in large language models","created":"2022-08-05","cited_by_count":76,"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":"2310.14540","title":"Evaluating Spatial Understanding of Large Language Models","created":"2023-10-23","cited_by_count":66,"area":null},{"id":"2404.03622","title":"Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models","created":"2024-04-04","cited_by_count":66,"area":"lr"},{"id":"2209.01515","title":"Do Large Language Models know what humans know?","created":"2022-09-04","cited_by_count":60,"area":null},{"id":"2411.04427","title":"One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversity","created":"2024-11-07","cited_by_count":58,"area":"alignment"},{"id":"2405.09605","title":"Elements of World Knowledge (EWoK): A Cognition-Inspired Framework for Evaluating Basic World Knowledge in Language Models","created":"2024-05-15","cited_by_count":55,"area":"wm"},{"id":"2501.00070","title":"ICLR: In-Context Learning of Representations","created":"2024-12-29","cited_by_count":50,"area":null},{"id":"2310.03249","title":"Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoning","created":"2023-10-05","cited_by_count":49,"area":"lr"},{"id":"2302.01308","title":"Large language models predict human sensory judgments across six modalities","created":"2023-02-02","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":"2212.01488","title":"Event knowledge in large language models: the gap between the impossible and the unlikely","created":"2022-12-02","cited_by_count":45,"area":null},{"id":"2407.02511","title":"LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planning","created":"2024-06-20","cited_by_count":45,"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":"2401.01862","title":"A Vision Check-up for Language Models","created":"2024-01-03","cited_by_count":36,"area":null},{"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":"2405.21030","title":"Standards for Belief Representations in LLMs","created":"2024-05-31","cited_by_count":30,"area":null},{"id":"2301.06627","title":"Dissociating language and thought in large language models","created":"2023-01-16","cited_by_count":29,"area":"lr"},{"id":"2302.06555","title":"Do Vision and Language Models Share Concepts? A Vector Space Alignment Study","created":"2023-02-13","cited_by_count":27,"area":null},{"id":"2311.08398","title":"Are Large Language Models Temporally Grounded?","created":"2023-11-14","cited_by_count":27,"area":null},{"id":"2502.03214","title":"iVISPAR -- An Interactive Visual-Spatial Reasoning Benchmark for VLMs","created":"2025-02-05","cited_by_count":25,"area":"lr"},{"id":"2407.17773","title":"KiVA: Kid-inspired Visual Analogies for Testing Large Multimodal Models","created":"2024-07-25","cited_by_count":24,"area":"lr"},{"id":"2310.19671","title":"Large Language Models: The Need for Nuance in Current Debates and a Pragmatic Perspective on Understanding","created":"2023-10-30","cited_by_count":20,"area":null},{"id":"2305.14057","title":"Can Language Models Understand Physical Concepts?","created":"2023-05-23","cited_by_count":19,"area":null},{"id":"2109.07971","title":"Do Language Models Know the Way to Rome?","created":"2021-09-16","cited_by_count":18,"area":null},{"id":"2502.08009","title":"The Geometry of Prompting: Unveiling Distinct Mechanisms of Task Adaptation in Language Models","created":"2025-02-11","cited_by_count":18,"area":null},{"id":"2306.00503","title":"MEWL: Few-shot multimodal word learning with referential uncertainty","created":"2023-06-01","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":"2210.01963","title":"COMPS: Conceptual Minimal Pair Sentences for testing Robust Property Knowledge and its Inheritance in Pre-trained Language Models","created":"2022-10-05","cited_by_count":15,"area":null},{"id":"2402.16998","title":"What Do Language Models Hear? Probing for Auditory Representations in Language Models","created":"2024-02-26","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":"2407.11015","title":"Does ChatGPT Have a Mind?","created":"2024-06-27","cited_by_count":14,"area":null},{"id":"2302.12239","title":"What makes a language easy to deep-learn? Deep neural networks and humans similarly benefit from compositional structure","created":"2023-02-23","cited_by_count":13,"area":null},{"id":"2410.00872","title":"Do Music Generation Models Encode Music Theory?","created":"2024-10-01","cited_by_count":13,"area":null},{"id":"2305.02469","title":"The System Model and the User Model: Exploring AI Dashboard Design","created":"2023-05-04","cited_by_count":12,"area":null},{"id":"2410.22590","title":"Characterizing the Role of Similarity in the Property Inferences of Language Models","created":"2024-10-29","cited_by_count":11,"area":null},{"id":"2503.04421","title":"Revisiting the Othello World Model Hypothesis","created":"2025-03-06","cited_by_count":11,"area":"wm"},{"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":"2507.20333","title":"The Blessing and Curse of Dimensionality in Safety Alignment","created":"2025-07-27","cited_by_count":10,"area":"alignment"},{"id":"2311.02171","title":"Emergence of Abstract State Representations in Embodied Sequence Modeling","created":"2023-11-03","cited_by_count":9,"area":null},{"id":"2406.17513","title":"Brittle Minds, Fixable Activations: Understanding Belief Representations in Language Models","created":"2024-06-25","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":"2312.16257","title":"More than Correlation: Do Large Language Models Learn Causal Representations of Space?","created":"2023-12-26","cited_by_count":7,"area":null},{"id":"2404.12145","title":"From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using Multisense Consistency","created":"2024-04-18","cited_by_count":7,"area":null},{"id":"2510.02425","title":"Words That Make Language Models Perceive","created":"2025-10-02","cited_by_count":7,"area":null},{"id":"2306.01930","title":"Structural Similarities Between Language Models and Neural Response Measurements","created":"2023-06-02","cited_by_count":6,"area":null},{"id":"2504.12187","title":"What Do Large Language Models Know? Tacit Knowledge as a Potential Causal-Explanatory Structure","created":"2025-04-16","cited_by_count":6,"area":null},{"id":"2505.19825","title":"Position: Foundation Models for Tabular Data within Systemic Contexts Need Grounding","created":"2025-05-26","cited_by_count":6,"area":null},{"id":"2206.08823","title":"Language with Vision: a Study on Grounded Word and Sentence Embeddings","created":"2022-06-17","cited_by_count":5,"area":null},{"id":"2308.09720","title":"On the Unexpected Abilities of Large Language Models","created":"2023-08-09","cited_by_count":5,"area":null},{"id":"2504.06393","title":"The Zero Body Problem: Probing LLM Use of Sensory Language","created":"2025-04-08","cited_by_count":5,"area":null},{"id":"2209.08982","title":"How to Adapt Pre-trained Vision-and-Language Models to a Text-only Input?","created":"2022-09-19","cited_by_count":4,"area":null},{"id":"2311.13105","title":"Perceptual Structure in the Absence of Grounding for LLMs: The Impact of Abstractedness and Subjectivity in Color Language","created":"2023-11-22","cited_by_count":4,"area":null},{"id":"2312.03881","title":"FoMo Rewards: Can we cast foundation models as reward functions?","created":"2023-12-06","cited_by_count":4,"area":null},{"id":"2410.08255","title":"Investigating Representation Universality: Case Study on Genealogical Representations","created":"2024-10-10","cited_by_count":4,"area":null},{"id":"2502.01628","title":"Harmonic Loss Trains Interpretable AI Models","created":"2025-02-03","cited_by_count":4,"area":null},{"id":"2508.11536","title":"Language models align with brain regions that represent concepts across modalities","created":"2025-08-15","cited_by_count":4,"area":null},{"id":"2508.19851","title":"Tracking World States with Language Models: State-Based Evaluation Using Chess","created":"2025-08-27","cited_by_count":4,"area":"wm"},{"id":"2604.07886","title":"Linear Representations of Hierarchical Concepts in Language Models","created":"2026-04-09","cited_by_count":4,"area":"mechinterp"},{"id":"2310.05481","title":"Cabbage Sweeter than Cake? Analysing the Potential of Large Language Models for Learning Conceptual Spaces","created":"2023-10-09","cited_by_count":3,"area":null},{"id":"2311.09308","title":"Divergences between Language Models and Human Brains","created":"2023-11-15","cited_by_count":3,"area":null},{"id":"2505.18575","title":"Response Uncertainty and Probe Modeling: Two Sides of the Same Coin in LLM Interpretability?","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2506.02701","title":"On Entity Identification in Language Models","created":"2025-06-03","cited_by_count":3,"area":"mechinterp"},{"id":"2506.03994","title":"Seeing What Tastes Good: Revisiting Multimodal Distributional Semantics in the Billion Parameter Era","created":"2025-06-04","cited_by_count":3,"area":null},{"id":"2506.11807","title":"Are Multimodal Large Language Models Pragmatically Competent Listeners in Simple Reference Resolution Tasks?","created":"2025-06-13","cited_by_count":3,"area":"mllm"},{"id":"2506.16370","title":"Can structural correspondences ground real world representational content in Large Language Models?","created":"2025-06-19","cited_by_count":3,"area":null},{"id":"2402.15337","title":"Ranking Entities along Conceptual Space Dimensions with LLMs: An Analysis of Fine-Tuning Strategies","created":"2024-02-23","cited_by_count":2,"area":null},{"id":"2410.16645","title":"Chatting with Bots: AI, Speech Acts, and the Edge of Assertion","created":"2024-10-22","cited_by_count":2,"area":null},{"id":"2502.01432","title":"Emergent Stack Representations in Modeling Counter Languages Using Transformers","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2502.20469","title":"Shades of Zero: Distinguishing Impossibility from Inconceivability","created":"2025-02-27","cited_by_count":2,"area":null},{"id":"2505.10861","title":"Improving the Data-efficiency of Reinforcement Learning by Warm-starting with LLM","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2506.06006","title":"Can VLMs Predict Future States? Bootstrapping World Models from Inverse Dynamics","created":"2025-06-06","cited_by_count":2,"area":"wm"},{"id":"2508.19791","title":"Color Bind: Exploring Color Perception in Text-to-Image Models","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2510.09556","title":"WUGNECTIVES: Novel Entity Inferences of Language Models from Discourse Connectives","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2407.13765","title":"Latent Causal Probing: A Formal Perspective on Probing with Causal Models of Data","created":"2024-07-18","cited_by_count":1,"area":null},{"id":"2409.09378","title":"Prevailing Research Areas for Music AI in the Era of Foundation Models","created":"2024-09-14","cited_by_count":1,"area":null},{"id":"2410.00519","title":"Exploring the Learning Capabilities of Language Models using LEVERWORLDS","created":"2024-10-01","cited_by_count":1,"area":null},{"id":"2503.09481","title":"BAMBI: Developing Baby Language Models for Italian","created":"2025-03-12","cited_by_count":1,"area":null},{"id":"2504.07965","title":"Cat, Rat, Meow: On the Alignment of Language Model and Human Term-Similarity Judgments","created":"2025-04-10","cited_by_count":1,"area":"alignment"},{"id":"2506.00003","title":"Probing Audio-Generation Capabilities of Text-Based Language Models","created":"2025-05-04","cited_by_count":1,"area":null},{"id":"2509.08093","title":"Evolution and compression in LLMs: On the emergence of human-aligned categorization","created":"2025-09-09","cited_by_count":1,"area":null},{"id":"2603.07474","title":"Cross-Modal Taxonomic Generalization in (Vision-) Language Models","created":"2026-03-08","cited_by_count":1,"area":null},{"id":"2605.06965","title":"AI and Consciousness: Shifting Focus Towards Tractable Questions","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.27970","title":"Geometry of Human Perceptual Domains Emerges Transiently in LLM Representations","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2206.15381","title":"How direct is the link between words and images?","created":"2022-06-30","cited_by_count":0,"area":null}],"next_cursor":"100"}