{"total":37,"rows":[{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876,"area":null},{"id":"2104.06644","title":"Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little","created":"2021-04-14","cited_by_count":177,"area":null},{"id":"2204.08831","title":"Probing for the Usage of Grammatical Number","created":"2022-04-19","cited_by_count":59,"area":null},{"id":"2104.03869","title":"Probing BERT in Hyperbolic Spaces","created":"2021-04-08","cited_by_count":50,"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":"2105.14002","title":"What if This Modified That? Syntactic Interventions via Counterfactual Embeddings","created":"2021-05-28","cited_by_count":39,"area":null},{"id":"2103.11072","title":"Local Interpretations for Explainable Natural Language Processing: A Survey","created":"2021-03-20","cited_by_count":31,"area":null},{"id":"2105.10185","title":"A Non-Linear Structural Probe","created":"2021-05-21","cited_by_count":31,"area":null},{"id":"2106.02559","title":"Do Syntactic Probes Probe Syntax? Experiments with Jabberwocky Probing","created":"2021-06-04","cited_by_count":28,"area":null},{"id":"2109.03853","title":"A Bayesian Framework for Information-Theoretic Probing","created":"2021-09-08","cited_by_count":22,"area":null},{"id":"2510.00296","title":"Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT","created":"2025-09-30","cited_by_count":17,"area":null},{"id":"2206.11719","title":"AST-Probe: Recovering abstract syntax trees from hidden representations of pre-trained language models","created":"2022-06-23","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":"2210.07352","title":"Predicting Fine-Tuning Performance with Probing","created":"2022-10-13","cited_by_count":13,"area":null},{"id":"2204.09722","title":"When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes","created":"2022-04-20","cited_by_count":12,"area":null},{"id":"2103.01819","title":"The Rediscovery Hypothesis: Language Models Need to Meet Linguistics","created":"2021-03-02","cited_by_count":7,"area":null},{"id":"2202.09166","title":"Evaluating the Construct Validity of Text Embeddings with Application to Survey Questions","created":"2022-02-18","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":"2311.08287","title":"How Well Do Large Language Models Understand Syntax? An Evaluation by Asking Natural Language Questions","created":"2023-11-14","cited_by_count":7,"area":null},{"id":"2110.08887","title":"Schr\\\"odinger's Tree -- On Syntax and Neural Language Models","created":"2021-10-17","cited_by_count":6,"area":null},{"id":"2201.08214","title":"A Latent-Variable Model for Intrinsic Probing","created":"2022-01-20","cited_by_count":5,"area":null},{"id":"2211.06420","title":"The Architectural Bottleneck Principle","created":"2022-11-11","cited_by_count":5,"area":null},{"id":"2406.02335","title":"Probing the Category of Verbal Aspect in Transformer Language Models","created":"2024-06-04","cited_by_count":5,"area":null},{"id":"2205.10238","title":"Visualizing and Explaining Language Models","created":"2022-04-30","cited_by_count":4,"area":null},{"id":"2406.11930","title":"A Critical Study of What Code-LLMs (Do Not) Learn","created":"2024-06-17","cited_by_count":4,"area":null},{"id":"2412.05353","title":"Incremental Sentence Processing Mechanisms in Autoregressive Transformer Language Models","created":"2024-12-06","cited_by_count":4,"area":null},{"id":"2102.00827","title":"Automatic Expansion of Domain-Specific Affective Models for Web Intelligence Applications","created":"2021-02-01","cited_by_count":2,"area":null},{"id":"2206.04935","title":"Sort by Structure: Language Model Ranking as Dependency Probing","created":"2022-06-10","cited_by_count":2,"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":"2109.04921","title":"Examining Cross-lingual Contextual Embeddings with Orthogonal Structural Probes","created":"2021-09-10","cited_by_count":1,"area":null},{"id":"2404.14270","title":"What do Transformers Know about Government?","created":"2024-04-22","cited_by_count":1,"area":null},{"id":"2407.08890","title":"DeepCodeProbe: Towards Understanding What Models Trained on Code Learn","created":"2024-07-11","cited_by_count":1,"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":"2412.01131","title":"A Comprehensive Evaluation of Semantic Relation Knowledge of Pretrained Language Models and Humans","created":"2024-12-02","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":"2602.06774","title":"Towards Understanding What State Space Models Learn About Code","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2504.00831","title":"Example-Based Concept Analysis Framework for Deep Weather Forecast Models","created":"2025-04-01","cited_by_count":0,"area":null}],"next_cursor":null}