{"total":40,"rows":[{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334,"area":null},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2108.13138","title":"Neuron-level Interpretation of Deep NLP Models: A Survey","created":"2021-08-30","cited_by_count":81,"area":null},{"id":"2211.07349","title":"Finding Skill Neurons in Pre-trained Transformer-based Language Models","created":"2022-11-14","cited_by_count":66,"area":null},{"id":"2110.07483","title":"On the Pitfalls of Analyzing Individual Neurons in Language Models","created":"2021-10-14","cited_by_count":62,"area":null},{"id":"2204.08831","title":"Probing for the Usage of Grammatical Number","created":"2022-04-19","cited_by_count":59,"area":null},{"id":"2205.07237","title":"Discovering Latent Concepts Learned in BERT","created":"2022-05-15","cited_by_count":56,"area":null},{"id":"2406.13229","title":"Probing the Emergence of Cross-lingual Alignment during LLM Training","created":"2024-06-19","cited_by_count":39,"area":null},{"id":"2305.19911","title":"Neuron to Graph: Interpreting Language Model Neurons at Scale","created":"2023-05-31","cited_by_count":27,"area":null},{"id":"2404.18923","title":"Holmes: A Benchmark to Assess the Linguistic Competence of Language Models","created":"2024-04-29","cited_by_count":26,"area":null},{"id":"2105.07452","title":"How is BERT surprised? Layerwise detection of linguistic anomalies","created":"2021-05-16","cited_by_count":24,"area":null},{"id":"2109.03853","title":"A Bayesian Framework for Information-Theoretic Probing","created":"2021-09-08","cited_by_count":22,"area":null},{"id":"2206.13288","title":"Discovering Salient Neurons in Deep NLP Models","created":"2022-06-27","cited_by_count":21,"area":null},{"id":"2305.13386","title":"Can LLMs facilitate interpretation of pre-trained language models?","created":"2023-05-22","cited_by_count":16,"area":null},{"id":"2310.18443","title":"Towards a fuller understanding of neurons with Clustered Compositional Explanations","created":"2023-10-27","cited_by_count":15,"area":null},{"id":"2205.02023","title":"Same Neurons, Different Languages: Probing Morphosyntax in Multilingual Pre-trained Models","created":"2022-05-04","cited_by_count":14,"area":null},{"id":"2110.08388","title":"Probing as Quantifying Inductive Bias","created":"2021-10-15","cited_by_count":12,"area":null},{"id":"2305.17073","title":"NeuroX Library for Neuron Analysis of Deep NLP Models","created":"2023-05-26","cited_by_count":11,"area":null},{"id":"2404.18533","title":"Evaluating Readability and Faithfulness of Concept-based Explanations","created":"2024-04-29","cited_by_count":10,"area":null},{"id":"2411.07474","title":"Controlled Evaluation of Syntactic Knowledge in Multilingual Language Models","created":"2024-11-12","cited_by_count":10,"area":null},{"id":"2301.12608","title":"Evaluating Neuron Interpretation Methods of NLP Models","created":"2023-01-30","cited_by_count":8,"area":null},{"id":"2211.04281","title":"SocioProbe: What, When, and Where Language Models Learn about Sociodemographics","created":"2022-11-08","cited_by_count":7,"area":null},{"id":"2403.04872","title":"Code-Mixed Probes Show How Pre-Trained Models Generalise On Code-Switched Text","created":"2024-03-07","cited_by_count":7,"area":null},{"id":"2106.01060","title":"John praised Mary because he? Implicit Causality Bias and Its Interaction with Explicit Cues in LMs","created":"2021-06-02","cited_by_count":5,"area":null},{"id":"2201.08214","title":"A Latent-Variable Model for Intrinsic Probing","created":"2022-01-20","cited_by_count":5,"area":null},{"id":"2310.15513","title":"A Joint Matrix Factorization Analysis of Multilingual Representations","created":"2023-10-24","cited_by_count":5,"area":null},{"id":"2311.07497","title":"Multilingual Nonce Dependency Treebanks: Understanding how Language Models represent and process syntactic structure","created":"2023-11-13","cited_by_count":5,"area":null},{"id":"2105.08039","title":"Fine-grained Interpretation and Causation Analysis in Deep NLP Models","created":"2021-05-17","cited_by_count":4,"area":null},{"id":"2202.12801","title":"On the data requirements of probing","created":"2022-02-25","cited_by_count":4,"area":null},{"id":"2206.00259","title":"IDANI: Inference-time Domain Adaptation via Neuron-level Interventions","created":"2022-06-01","cited_by_count":4,"area":null},{"id":"2210.12206","title":"Probing with Noise: Unpicking the Warp and Weft of Embeddings","created":"2022-10-21","cited_by_count":3,"area":null},{"id":"2304.14333","title":"Idioms, Probing and Dangerous Things: Towards Structural Probing for Idiomaticity in Vector Space","created":"2023-04-27","cited_by_count":3,"area":null},{"id":"2504.14766","title":"Disentangling Linguistic Features with Dimension-Wise Analysis of Vector Embeddings","created":"2025-04-20","cited_by_count":2,"area":null},{"id":"2104.00789","title":"Do RNN States Encode Abstract Phonological Processes?","created":"2021-04-01","cited_by_count":1,"area":null},{"id":"2106.03631","title":"Unsupervised Representation Disentanglement of Text: An Evaluation on Synthetic Datasets","created":"2021-06-07","cited_by_count":1,"area":null},{"id":"2401.16731","title":"Towards Generating Informative Textual Description for Neurons in Language Models","created":"2024-01-30","cited_by_count":1,"area":null},{"id":"2410.13396","title":"Linguistically Grounded Analysis of Language Models using Shapley Head Values","created":"2024-10-17","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":"2106.06964","title":"Shape of Elephant: Study of Macro Properties of Word Embeddings Spaces","created":"2021-06-13","cited_by_count":0,"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}