{"total":42,"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":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"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":"2105.14686","title":"Fully Hyperbolic Neural Networks","created":"2021-05-31","cited_by_count":108,"area":null},{"id":"2403.03867","title":"On the Origins of Linear Representations in Large Language Models","created":"2024-03-06","cited_by_count":79,"area":null},{"id":"2109.09234","title":"Conditional probing: measuring usable information beyond a baseline","created":"2021-09-19","cited_by_count":62,"area":null},{"id":"2303.08117","title":"Do Transformers Parse while Predicting the Masked Word?","created":"2023-03-14","cited_by_count":48,"area":null},{"id":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"area":null},{"id":"2106.14282","title":"A Closer Look at How Fine-tuning Changes BERT","created":"2021-06-27","cited_by_count":42,"area":null},{"id":"2202.13852","title":"Hyperbolic Graph Neural Networks: A Review of Methods and Applications","created":"2022-02-28","cited_by_count":40,"area":null},{"id":"2206.14017","title":"Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsing","created":"2022-06-28","cited_by_count":30,"area":null},{"id":"2306.08158","title":"Sociodemographic Bias in Language Models: A Survey and Forward Path","created":"2023-06-13","cited_by_count":28,"area":null},{"id":"2401.11374","title":"Language Models as Hierarchy Encoders","created":"2024-01-21","cited_by_count":28,"area":null},{"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":"2412.05571","title":"A polar coordinate system represents syntax in large language models","created":"2024-12-07","cited_by_count":25,"area":null},{"id":"2109.04740","title":"How Does Fine-tuning Affect the Geometry of Embedding Space: A Case Study on Isotropy","created":"2021-09-10","cited_by_count":23,"area":null},{"id":"2404.09554","title":"Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda","created":"2024-04-15","cited_by_count":22,"area":null},{"id":"2110.10470","title":"Interpreting Deep Learning Models in Natural Language Processing: A Review","created":"2021-10-20","cited_by_count":19,"area":null},{"id":"2504.08896","title":"Position: Beyond Euclidean -- Foundation Models Should Embrace Non-Euclidean Geometries","created":"2025-04-11","cited_by_count":18,"area":null},{"id":"2109.05958","title":"Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids' Representations","created":"2021-09-13","cited_by_count":16,"area":null},{"id":"2304.13301","title":"Prompting GPT-3.5 for Text-to-SQL with De-semanticization and Skeleton Retrieval","created":"2023-04-26","cited_by_count":16,"area":null},{"id":"2204.06201","title":"Probing for Constituency Structure in Neural Language Models","created":"2022-04-13","cited_by_count":14,"area":null},{"id":"2504.08912","title":"HyperCore: The Core Framework for Building Hyperbolic Foundation Models with Comprehensive Modules","created":"2025-04-11","cited_by_count":12,"area":null},{"id":"2204.12822","title":"A Survey on XAI for 5G and Beyond Security: Technical Aspects, Challenges and Research Directions","created":"2022-04-27","cited_by_count":9,"area":null},{"id":"2205.02047","title":"Hyperbolic Relevance Matching for Neural Keyphrase Extraction","created":"2022-05-04","cited_by_count":7,"area":null},{"id":"2206.01512","title":"Latent Topology Induction for Understanding Contextualized Representations","created":"2022-06-03","cited_by_count":7,"area":null},{"id":"2310.05884","title":"A Meta-Learning Perspective on Transformers for Causal Language Modeling","created":"2023-10-09","cited_by_count":5,"area":null},{"id":"2402.12151","title":"Transformer-based Causal Language Models Perform Clustering","created":"2024-02-19","cited_by_count":5,"area":null},{"id":"2508.03211","title":"Probing Syntax in Large Language Models: Successes and Remaining Challenges","created":"2025-08-05","cited_by_count":5,"area":null},{"id":"2203.01063","title":"Discontinuous Constituency and BERT: A Case Study of Dutch","created":"2022-03-02","cited_by_count":3,"area":null},{"id":"2206.04285","title":"A Unification Framework for Euclidean and Hyperbolic Graph Neural Networks","created":"2022-06-09","cited_by_count":2,"area":null},{"id":"2312.09670","title":"Probing Pretrained Language Models with Hierarchy Properties","created":"2023-12-15","cited_by_count":2,"area":null},{"id":"2602.16161","title":"Emotion Collider: Dual Hyperbolic Mirror Manifolds for Sentiment Recovery via Anti Emotion Reflection","created":"2026-02-18","cited_by_count":2,"area":null},{"id":"2203.00162","title":"Do Transformers know symbolic rules, and would we know if they did?","created":"2022-02-19","cited_by_count":1,"area":null},{"id":"2210.06928","title":"Sentence Ambiguity, Grammaticality and Complexity Probes","created":"2022-10-13","cited_by_count":1,"area":null},{"id":"2402.02478","title":"Why are hyperbolic neural networks effective? A study on hierarchical representation capability","created":"2024-02-04","cited_by_count":1,"area":null},{"id":"2503.05491","title":"Statistical Deficiency for Task Inclusion Estimation","created":"2025-03-07","cited_by_count":1,"area":null},{"id":"2510.09790","title":"Mapping Semantic & Syntactic Relationships with Geometric Rotation","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2601.19926","title":"The Grammar of Transformers: A Systematic Review of Interpretability Research on Syntactic Knowledge in Language Models","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2605.05197","title":"Implicit Representations of Grammaticality in Language Models","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2310.11363","title":"Disentangling the Linguistic Competence of Privacy-Preserving BERT","created":"2023-10-17","cited_by_count":0,"area":null},{"id":"2406.05315","title":"Aligned at the Start: Conceptual Groupings in LLM Embeddings","created":"2024-06-08","cited_by_count":0,"area":null}],"next_cursor":null}