{"total":39,"rows":[{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2312.12936","title":"Concept-based Explainable Artificial Intelligence: A Survey","created":"2023-12-20","cited_by_count":98,"area":null},{"id":"2110.03212","title":"Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates","created":"2021-10-07","cited_by_count":27,"area":null},{"id":"2109.02738","title":"Does BERT Learn as Humans Perceive? Understanding Linguistic Styles through Lexica","created":"2021-09-06","cited_by_count":23,"area":null},{"id":"2310.19660","title":"Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneck","created":"2023-10-30","cited_by_count":22,"area":null},{"id":"2204.05426","title":"ProtoTEx: Explaining Model Decisions with Prototype Tensors","created":"2022-04-11","cited_by_count":21,"area":null},{"id":"2309.13391","title":"D-Separation for Causal Self-Explanation","created":"2023-09-23","cited_by_count":21,"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":"2306.14115","title":"Towards Trustworthy Explanation: On Causal Rationalization","created":"2023-06-25","cited_by_count":19,"area":null},{"id":"2501.15638","title":"A Comprehensive Survey on Self-Interpretable Neural Networks","created":"2025-01-26","cited_by_count":18,"area":null},{"id":"2206.11083","title":"Investigating the Benefits of Free-Form Rationales","created":"2022-05-25","cited_by_count":13,"area":null},{"id":"2305.03117","title":"Are Human Explanations Always Helpful? Towards Objective Evaluation of Human Natural Language Explanations","created":"2023-05-04","cited_by_count":13,"area":null},{"id":"2404.12545","title":"Latent Concept-based Explanation of NLP Models","created":"2024-04-18","cited_by_count":13,"area":null},{"id":"2305.04492","title":"MGR: Multi-generator Based Rationalization","created":"2023-05-08","cited_by_count":12,"area":null},{"id":"2502.03391","title":"Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient Reasons","created":"2025-02-05","cited_by_count":12,"area":null},{"id":"2305.12710","title":"Beyond Labels: Empowering Human Annotators with Natural Language Explanations through a Novel Active-Learning Architecture","created":"2023-05-22","cited_by_count":10,"area":null},{"id":"2401.01549","title":"Towards Modeling Uncertainties of Self-explaining Neural Networks via Conformal Prediction","created":"2024-01-03","cited_by_count":10,"area":null},{"id":"2103.15429","title":"Efficient Explanations from Empirical Explainers","created":"2021-03-29","cited_by_count":9,"area":null},{"id":"2203.08788","title":"Are Shortest Rationales the Best Explanations for Human Understanding?","created":"2022-03-16","cited_by_count":8,"area":null},{"id":"2203.08979","title":"Speaker Information Can Guide Models to Better Inductive Biases: A Case Study On Predicting Code-Switching","created":"2022-03-16","cited_by_count":6,"area":null},{"id":"2503.06202","title":"Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilization","created":"2025-03-08","cited_by_count":6,"area":null},{"id":"2505.02118","title":"Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets","created":"2025-05-04","cited_by_count":6,"area":null},{"id":"2212.03396","title":"Learning to Select Prototypical Parts for Interpretable Sequential Data Modeling","created":"2022-12-07","cited_by_count":4,"area":null},{"id":"2504.05625","title":"Model-Agnostic Policy Explanations with Large Language Models","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2210.07469","title":"StyLEx: Explaining Style Using Human Lexical Annotations","created":"2022-10-14","cited_by_count":3,"area":null},{"id":"2402.17914","title":"Extracting Lexical Features from Dialects via Interpretable Dialect Classifiers","created":"2024-02-27","cited_by_count":3,"area":null},{"id":"2406.14335","title":"Linearly-Interpretable Concept Embedding Models for Text Analysis","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2310.16753","title":"PROMINET: Prototype-based Multi-View Network for Interpretable Email Response Prediction","created":"2023-10-25","cited_by_count":2,"area":null},{"id":"2410.17546","title":"Advancing Interpretability in Text Classification through Prototype Learning","created":"2024-10-23","cited_by_count":2,"area":null},{"id":"2108.09394","title":"Beyond Tracking: Using Deep Learning to Discover Novel Interactions in Biological Swarms","created":"2021-08-20","cited_by_count":1,"area":null},{"id":"2203.07640","title":"Unsupervised Keyphrase Extraction via Interpretable Neural Networks","created":"2022-03-15","cited_by_count":1,"area":null},{"id":"2302.00894","title":"How to choose \"Good\" Samples for Text Data Augmentation","created":"2023-02-02","cited_by_count":1,"area":null},{"id":"2311.08644","title":"Wrapper Boxes: Faithful Attribution of Model Predictions to Training Data","created":"2023-11-15","cited_by_count":1,"area":null},{"id":"2404.13645","title":"PEACH: Pretrained-embedding Explanation Across Contextual and Hierarchical Structure","created":"2024-04-21","cited_by_count":1,"area":null},{"id":"2505.20293","title":"Enhancing the Comprehensibility of Text Explanations via Unsupervised Concept Discovery","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2304.01638","title":"Multidimensional Perceptron for Efficient and Explainable Long Text Classification","created":"2023-04-04","cited_by_count":0,"area":null},{"id":"2311.02237","title":"Explainable Authorship Identification in Cultural Heritage Applications: Analysis of a New Perspective","created":"2023-11-03","cited_by_count":0,"area":null},{"id":"2406.10086","title":"Discovering influential text using convolutional neural networks","created":"2024-06-14","cited_by_count":0,"area":null},{"id":"2503.12978","title":"Enhancing Job Salary Prediction with Disentangled Composition Effect Modeling: A Neural Prototyping Approach","created":"2025-03-17","cited_by_count":0,"area":null}],"next_cursor":null}