{"total":124,"rows":[{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637,"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":"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":"2310.02207","title":"Language Models Represent Space and Time","created":"2023-10-03","cited_by_count":316,"area":null},{"id":"2309.14316","title":"Physics of Language Models: Part 3.1, Knowledge Storage and Extraction","created":"2023-09-25","cited_by_count":270,"area":null},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221,"area":null},{"id":"2303.02536","title":"Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations","created":"2023-03-05","cited_by_count":209,"area":null},{"id":"2308.09124","title":"Linearity of Relation Decoding in Transformer Language Models","created":"2023-08-17","cited_by_count":200,"area":null},{"id":"2212.03551","title":"Talking About Large Language Models","created":"2022-12-07","cited_by_count":175,"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":"2209.15162","title":"Linearly Mapping from Image to Text Space","created":"2022-09-30","cited_by_count":142,"area":null},{"id":"2210.13966","title":"The Debate Over Understanding in AI's Large Language Models","created":"2022-10-14","cited_by_count":142,"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":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2204.11454","title":"Natural Language to Code Translation with Execution","created":"2022-04-25","cited_by_count":124,"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":"2305.08809","title":"Interpretability at Scale: Identifying Causal Mechanisms in Alpaca","created":"2023-05-15","cited_by_count":103,"area":null},{"id":"2107.02794","title":"Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning","created":"2021-07-06","cited_by_count":85,"area":null},{"id":"2208.02957","title":"Meaning without reference in large language models","created":"2022-08-05","cited_by_count":76,"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":"2411.04986","title":"The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities","created":"2024-11-07","cited_by_count":69,"area":null},{"id":"2308.01399","title":"Learning to Model the World with Language","created":"2023-07-31","cited_by_count":68,"area":null},{"id":"2403.10949","title":"SelfIE: Self-Interpretation of Large Language Model Embeddings","created":"2024-03-16","cited_by_count":67,"area":null},{"id":"2310.14540","title":"Evaluating Spatial Understanding of Large Language Models","created":"2023-10-23","cited_by_count":66,"area":null},{"id":"2209.01515","title":"Do Large Language Models know what humans know?","created":"2022-09-04","cited_by_count":60,"area":null},{"id":"2412.08686","title":"LatentQA: Teaching LLMs to Decode Activations Into Natural Language","created":"2024-12-11","cited_by_count":51,"area":null},{"id":"2501.00070","title":"ICLR: In-Context Learning of Representations","created":"2024-12-29","cited_by_count":50,"area":null},{"id":"2310.18168","title":"Personas as a Way to Model Truthfulness in Language Models","created":"2023-10-27","cited_by_count":47,"area":null},{"id":"2305.02363","title":"Entity Tracking in Language Models","created":"2023-05-03","cited_by_count":44,"area":null},{"id":"2406.12673","title":"Estimating Knowledge in Large Language Models Without Generating a Single Token","created":"2024-06-18","cited_by_count":40,"area":null},{"id":"2505.14685","title":"Language Models use Lookbacks to Track Beliefs","created":"2025-05-20","cited_by_count":39,"area":null},{"id":"2401.01862","title":"A Vision Check-up for Language Models","created":"2024-01-03","cited_by_count":36,"area":null},{"id":"2503.02854","title":"(How) Do Language Models Track State?","created":"2025-03-04","cited_by_count":34,"area":null},{"id":"2310.19619","title":"Towards A Holistic Landscape of Situated Theory of Mind in Large Language Models","created":"2023-10-30","cited_by_count":32,"area":null},{"id":"2305.20076","title":"Decision-Oriented Dialogue for Human-AI Collaboration","created":"2023-05-31","cited_by_count":29,"area":null},{"id":"2211.09748","title":"Probing for Incremental Parse States in Autoregressive Language Models","created":"2022-11-17","cited_by_count":24,"area":null},{"id":"2403.14859","title":"Log Probabilities Are a Reliable Estimate of Semantic Plausibility in Base and Instruction-Tuned Language Models","created":"2024-03-21","cited_by_count":24,"area":null},{"id":"2205.03472","title":"When a sentence does not introduce a discourse entity, Transformer-based models still sometimes refer to it","created":"2022-05-06","cited_by_count":23,"area":null},{"id":"2205.14288","title":"Few-shot Subgoal Planning with Language Models","created":"2022-05-28","cited_by_count":22,"area":null},{"id":"2210.04964","title":"Generating Executable Action Plans with Environmentally-Aware Language Models","created":"2022-10-10","cited_by_count":21,"area":null},{"id":"2302.01339","title":"Creating a Large Language Model of a Philosopher","created":"2023-02-02","cited_by_count":21,"area":null},{"id":"2402.19465","title":"Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models","created":"2024-02-29","cited_by_count":18,"area":null},{"id":"2405.03207","title":"A Philosophical Introduction to Language Models - Part II: The Way Forward","created":"2024-05-06","cited_by_count":18,"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":"2403.09053","title":"Towards a theory of model distillation","created":"2024-03-14","cited_by_count":15,"area":null},{"id":"2409.17027","title":"Counterfactual Token Generation in Large Language Models","created":"2024-09-25","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":"2505.17510","title":"Large Language Models Do Multi-Label Classification Differently","created":"2025-05-23","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":"2310.15004","title":"When Language Models Fall in Love: Animacy Processing in Transformer Language Models","created":"2023-10-23","cited_by_count":12,"area":null},{"id":"2311.08968","title":"Identifying Linear Relational Concepts in Large Language Models","created":"2023-11-15","cited_by_count":12,"area":null},{"id":"2302.02801","title":"LaMPP: Language Models as Probabilistic Priors for Perception and Action","created":"2023-02-03","cited_by_count":11,"area":null},{"id":"2405.14660","title":"Implicit In-context Learning","created":"2024-05-23","cited_by_count":11,"area":null},{"id":"2509.15714","title":"Once Upon a Time: Interactive Learning for Storytelling with Small Language Models","created":"2025-09-19","cited_by_count":11,"area":null},{"id":"2310.15047","title":"Implicit meta-learning may lead language models to trust more reliable sources","created":"2023-10-23","cited_by_count":10,"area":null},{"id":"2406.03707","title":"What Should Embeddings Embed? Autoregressive Models Represent Latent Generating Distributions","created":"2024-06-06","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":"2112.08583","title":"Does Pre-training Induce Systematic Inference? How Masked Language Models Acquire Commonsense Knowledge","created":"2021-12-16","cited_by_count":8,"area":null},{"id":"2210.07468","title":"Transparency Helps Reveal When Language Models Learn Meaning","created":"2022-10-14","cited_by_count":8,"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":"2410.05565","title":"Chain and Causal Attention for Efficient Entity Tracking","created":"2024-10-07","cited_by_count":8,"area":null},{"id":"2410.20221","title":"Generative linguistics contribution to artificial intelligence: Where this contribution lies?","created":"2024-10-26","cited_by_count":8,"area":null},{"id":"2411.19858","title":"What fifty-one years of Linguistics and Artificial Intelligence research tell us about their correlation: A scientometric analysis","created":"2024-11-29","cited_by_count":8,"area":null},{"id":"2112.00086","title":"Dyna-bAbI: unlocking bAbI's potential with dynamic synthetic benchmarking","created":"2021-11-30","cited_by_count":7,"area":null},{"id":"2306.03882","title":"Causal interventions expose implicit situation models for commonsense language understanding","created":"2023-06-06","cited_by_count":7,"area":null},{"id":"2312.14226","title":"Deep de Finetti: Recovering Topic Distributions from Large Language Models","created":"2023-12-21","cited_by_count":7,"area":null},{"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":"2405.17653","title":"InversionView: A General-Purpose Method for Reading Information from Neural Activations","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2407.12543","title":"Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationships","created":"2024-07-17","cited_by_count":7,"area":null},{"id":"2506.14276","title":"Don't throw the baby out with the bathwater: How and why deep learning for ARC","created":"2025-06-17","cited_by_count":7,"area":null},{"id":"2506.21812","title":"Towards Transparent AI: A Survey on Explainable Large Language Models","created":"2025-06-26","cited_by_count":7,"area":null},{"id":"2602.13540","title":"On Calibration of Large Language Models: From Response To Capability","created":"2026-02-14","cited_by_count":7,"area":null},{"id":"2211.07950","title":"Breakpoint Transformers for Modeling and Tracking Intermediate Beliefs","created":"2022-11-15","cited_by_count":6,"area":null},{"id":"2212.10012","title":"Language Modeling with Latent Situations","created":"2022-12-20","cited_by_count":6,"area":null},{"id":"2305.08495","title":"Similarity-weighted Construction of Contextualized Commonsense Knowledge Graphs for Knowledge-intense Argumentation Tasks","created":"2023-05-15","cited_by_count":6,"area":null},{"id":"2310.15372","title":"EpiK-Eval: Evaluation for Language Models as Epistemic Models","created":"2023-10-23","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":"2308.09720","title":"On the Unexpected Abilities of Large Language Models","created":"2023-08-09","cited_by_count":5,"area":null},{"id":"2405.09679","title":"Simulating Policy Impacts: Developing a Generative Scenario Writing Method to Evaluate the Perceived Effects of Regulation","created":"2024-05-15","cited_by_count":5,"area":null},{"id":"2307.02689","title":"Learning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement Learning","created":"2023-07-05","cited_by_count":4,"area":null},{"id":"2308.13782","title":"Planning with Logical Graph-based Language Model for Instruction Generation","created":"2023-08-26","cited_by_count":4,"area":null},{"id":"2310.16135","title":"Can You Follow Me? Testing Situational Understanding in ChatGPT","created":"2023-10-24","cited_by_count":4,"area":null},{"id":"2408.10437","title":"Understanding Generative AI Content with Embedding Models","created":"2024-08-19","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":"2206.05706","title":"CoSe-Co: Text Conditioned Generative CommonSense Contextualizer","created":"2022-06-12","cited_by_count":3,"area":null},{"id":"2210.10684","title":"Language Models Understand Us, Poorly","created":"2022-10-19","cited_by_count":3,"area":null},{"id":"2504.16871","title":"Exploring How LLMs Capture and Represent Domain-Specific Knowledge","created":"2025-04-23","cited_by_count":3,"area":null},{"id":"2509.21631","title":"Towards Transparent AI: A Survey on Explainable Language Models","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2510.22131","title":"Probing Neural Combinatorial Optimization Models","created":"2025-10-25","cited_by_count":3,"area":null},{"id":"2212.00281","title":"Localization vs. Semantics: Visual Representations in Unimodal and Multimodal Models","created":"2022-12-01","cited_by_count":2,"area":null},{"id":"2410.13054","title":"Systems with Switching Causal Relations: A Meta-Causal Perspective","created":"2024-10-16","cited_by_count":2,"area":null},{"id":"2410.18527","title":"Probing Ranking LLMs: A Mechanistic Analysis for Information Retrieval","created":"2024-10-24","cited_by_count":2,"area":null},{"id":"2410.20513","title":"Self-correction is Not An Innate Capability in Language Models","created":"2024-10-27","cited_by_count":2,"area":null},{"id":"2412.10558","title":"Too Big to Fool: Resisting Deception in Language Models","created":"2024-12-13","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":"2509.21456","title":"Diagnosing the Performance Trade-off in Moral Alignment: A Case Study on Gender Stereotypes","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2606.26749","title":"Structure Before Collapse: Transient semantic geometry in next-token prediction","created":"2026-06-25","cited_by_count":2,"area":null},{"id":"2407.11421","title":"States Hidden in Hidden States: Implicit Discrete State Representations Emerge in LLMs' Hidden States","created":"2024-07-16","cited_by_count":1,"area":null}],"next_cursor":"100"}