{"total":46,"rows":[{"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":"2204.06031","title":"A Review on Language Models as Knowledge Bases","created":"2022-04-12","cited_by_count":157,"area":null},{"id":"2201.11227","title":"Synchromesh: Reliable code generation from pre-trained language models","created":"2022-01-26","cited_by_count":156,"area":null},{"id":"2109.06129","title":"Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color","created":"2021-09-13","cited_by_count":119,"area":null},{"id":"2402.11917","title":"A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task","created":"2024-02-19","cited_by_count":49,"area":null},{"id":"2305.02363","title":"Entity Tracking in Language Models","created":"2023-05-03","cited_by_count":44,"area":null},{"id":"2204.03972","title":"Contrastive language and vision learning of general fashion concepts","created":"2022-04-08","cited_by_count":42,"area":null},{"id":"2110.08300","title":"The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail","created":"2021-10-15","cited_by_count":38,"area":null},{"id":"2208.12852","title":"What Do NLP Researchers Believe? Results of the NLP Community Metasurvey","created":"2022-08-26","cited_by_count":28,"area":null},{"id":"2109.10246","title":"Does Vision-and-Language Pretraining Improve Lexical Grounding?","created":"2021-09-21","cited_by_count":25,"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":"2208.10244","title":"Unit Testing for Concepts in Neural Networks","created":"2022-07-28","cited_by_count":23,"area":null},{"id":"2311.07811","title":"In-context Learning Generalizes, But Not Always Robustly: The Case of Syntax","created":"2023-11-13","cited_by_count":22,"area":null},{"id":"2204.12708","title":"On the Limitations of Dataset Balancing: The Lost Battle Against Spurious Correlations","created":"2022-04-27","cited_by_count":19,"area":null},{"id":"2302.09170","title":"KILM: Knowledge Injection into Encoder-Decoder Language Models","created":"2023-02-17","cited_by_count":19,"area":null},{"id":"2310.18348","title":"Meaning Representations from Trajectories in Autoregressive Models","created":"2023-10-23","cited_by_count":18,"area":null},{"id":"2105.12449","title":"LMMS Reloaded: Transformer-based Sense Embeddings for Disambiguation and Beyond","created":"2021-05-26","cited_by_count":17,"area":null},{"id":"2403.17368","title":"ChatGPT Rates Natural Language Explanation Quality Like Humans: But on Which Scales?","created":"2024-03-26","cited_by_count":17,"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":"2112.07874","title":"Linguistic Frameworks Go Toe-to-Toe at Neuro-Symbolic Language Modeling","created":"2021-12-15","cited_by_count":10,"area":null},{"id":"2209.12407","title":"Entailment Semantics Can Be Extracted from an Ideal Language Model","created":"2022-09-26","cited_by_count":10,"area":null},{"id":"2402.13956","title":"Can You Learn Semantics Through Next-Word Prediction? The Case of Entailment","created":"2024-02-21","cited_by_count":9,"area":null},{"id":"2405.05966","title":"Natural Language Processing RELIES on Linguistics","created":"2024-05-09","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":"2209.10254","title":"T5QL: Taming language models for SQL generation","created":"2022-09-21","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":"2507.08017","title":"Mechanistic Indicators of Understanding in Large Language Models","created":"2025-07-07","cited_by_count":8,"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":"2306.02388","title":"Commonsense Knowledge Transfer for Pre-trained Language Models","created":"2023-06-04","cited_by_count":5,"area":null},{"id":"2401.17703","title":"WSC+: Enhancing The Winograd Schema Challenge Using Tree-of-Experts","created":"2024-01-31","cited_by_count":5,"area":null},{"id":"2207.07025","title":"Learning to translate by learning to communicate","created":"2022-07-14","cited_by_count":4,"area":null},{"id":"2210.10684","title":"Language Models Understand Us, Poorly","created":"2022-10-19","cited_by_count":3,"area":null},{"id":"2310.16240","title":"Mixture-of-Linguistic-Experts Adapters for Improving and Interpreting Pre-trained Language Models","created":"2023-10-24","cited_by_count":2,"area":null},{"id":"2312.09532","title":"Grounding for Artificial Intelligence","created":"2023-12-15","cited_by_count":2,"area":null},{"id":"2505.20959","title":"Research Community Perspectives on \"Intelligence\" and Large Language Models","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2607.04926","title":"Input Pathways Shape Few-Shot, Not Zero-Shot, Binding in Tiny Transformers: A Fully-Enumerable Study","created":"2026-07-06","cited_by_count":2,"area":null},{"id":"2201.05334","title":"This Must Be the Place: Predicting Engagement of Online Communities in a Large-scale Distributed Campaign","created":"2022-01-14","cited_by_count":1,"area":null},{"id":"2205.07811","title":"Natural Language Specifications in Proof Assistants","created":"2022-05-16","cited_by_count":1,"area":null},{"id":"2305.15130","title":"On Degrees of Freedom in Defining and Testing Natural Language Understanding","created":"2023-05-24","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":"2112.11913","title":"Trees in transformers: a theoretical analysis of the Transformer's ability to represent trees","created":"2021-12-16","cited_by_count":0,"area":null},{"id":"2504.16884","title":"Do Large Language Models know who did what to whom?","created":"2025-04-23","cited_by_count":0,"area":null},{"id":"2605.31480","title":"Language Models Can Resolve Reference Compositionally, But It's Not Their Native Strength: The Case of the Personal Relation Task","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.18305","title":"The Information Shadow: Measuring Structural Limits on What Language Models Can Learn","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2608.28560","title":"A Formal Limitation on Learning Human Language From Textual Corpora","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.07474","title":"Where Should Language Sit in a Multimodal Model? Lessons from What Language Does to Human Perception and Cognition","created":"2026-09-07","cited_by_count":0,"area":null}],"next_cursor":null}