{"total":58,"rows":[{"id":"2108.13624","title":"Towards Out-Of-Distribution Generalization: A Survey","created":"2021-08-31","cited_by_count":436,"area":null},{"id":"2201.12872","title":"Discovering Invariant Rationales for Graph Neural Networks","created":"2022-01-30","cited_by_count":188,"area":null},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156,"area":null},{"id":"2302.13942","title":"Inseq: An Interpretability Toolkit for Sequence Generation Models","created":"2023-02-27","cited_by_count":78,"area":null},{"id":"2103.13084","title":"Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Cases","created":"2021-03-24","cited_by_count":77,"area":null},{"id":"2301.03282","title":"Universal Information Extraction as Unified Semantic Matching","created":"2023-01-09","cited_by_count":48,"area":null},{"id":"2204.03031","title":"VALUE: Understanding Dialect Disparity in NLU","created":"2022-04-06","cited_by_count":47,"area":null},{"id":"2301.07779","title":"Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection","created":"2023-01-18","cited_by_count":44,"area":null},{"id":"2210.06929","title":"On the Explainability of Natural Language Processing Deep Models","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2111.06206","title":"Defining and Quantifying the Emergence of Sparse Concepts in DNNs","created":"2021-11-11","cited_by_count":36,"area":null},{"id":"2204.11790","title":"Can Rationalization Improve Robustness?","created":"2022-04-25","cited_by_count":36,"area":null},{"id":"2205.05057","title":"Sensible AI: Re-imagining Interpretability and Explainability using Sensemaking Theory","created":"2022-05-10","cited_by_count":32,"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":"2109.06387","title":"Rationales for Sequential Predictions","created":"2021-09-14","cited_by_count":26,"area":null},{"id":"2410.09087","title":"Mechanistic?","created":"2024-10-07","cited_by_count":25,"area":"mechinterp"},{"id":"2301.08912","title":"Rationalization for Explainable NLP: A Survey","created":"2023-01-21","cited_by_count":22,"area":null},{"id":"2105.04837","title":"Rationalization through Concepts","created":"2021-05-11","cited_by_count":19,"area":null},{"id":"2104.13299","title":"From Human Explanation to Model Interpretability: A Framework Based on Weight of Evidence","created":"2021-04-27","cited_by_count":17,"area":null},{"id":"2109.01962","title":"Counterfactual Evaluation for Explainable AI","created":"2021-09-05","cited_by_count":15,"area":null},{"id":"2205.11097","title":"A Fine-grained Interpretability Evaluation Benchmark for Neural NLP","created":"2022-05-23","cited_by_count":15,"area":null},{"id":"2104.09420","title":"Everything Has a Cause: Leveraging Causal Inference in Legal Text Analysis","created":"2021-04-19","cited_by_count":14,"area":null},{"id":"2302.06975","title":"A Review of the Role of Causality in Developing Trustworthy AI Systems","created":"2023-02-14","cited_by_count":14,"area":null},{"id":"2404.01295","title":"Towards Safety and Helpfulness Balanced Responses via Controllable Large Language Models","created":"2024-04-01","cited_by_count":14,"area":null},{"id":"2101.03501","title":"Entropic Causal Inference: Identifiability and Finite Sample Results","created":"2021-01-10","cited_by_count":12,"area":null},{"id":"2212.07056","title":"On the Probability of Necessity and Sufficiency of Explaining Graph Neural Networks: A Lower Bound Optimization Approach","created":"2022-12-14","cited_by_count":11,"area":null},{"id":"2105.10719","title":"Can We Faithfully Represent Masked States to Compute Shapley Values on a DNN?","created":"2021-05-22","cited_by_count":10,"area":null},{"id":"2111.12490","title":"Matching Learned Causal Effects of Neural Networks with Domain Priors","created":"2021-11-24","cited_by_count":10,"area":null},{"id":"2109.07983","title":"Let the CAT out of the bag: Contrastive Attributed explanations for Text","created":"2021-09-16","cited_by_count":9,"area":null},{"id":"2210.14177","title":"Influence Functions for Sequence Tagging Models","created":"2022-10-25","cited_by_count":9,"area":null},{"id":"2305.15015","title":"Measuring Faithful and Plausible Visual Grounding in VQA","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2306.11485","title":"Explicit Syntactic Guidance for Neural Text Generation","created":"2023-06-20","cited_by_count":8,"area":null},{"id":"2106.06528","title":"Local Explanation of Dialogue Response Generation","created":"2021-06-11","cited_by_count":7,"area":null},{"id":"2305.02160","title":"Explaining Language Models' Predictions with High-Impact Concepts","created":"2023-05-03","cited_by_count":7,"area":null},{"id":"2310.16607","title":"On the Interplay between Fairness and Explainability","created":"2023-10-25","cited_by_count":7,"area":null},{"id":"2107.06217","title":"What classifiers know what they don't?","created":"2021-07-13","cited_by_count":6,"area":null},{"id":"2305.07132","title":"Tackling Interpretability in Audio Classification Networks with Non-negative Matrix Factorization","created":"2023-05-11","cited_by_count":5,"area":null},{"id":"2309.13965","title":"May I Ask a Follow-up Question? Understanding the Benefits of Conversations in Neural Network Explainability","created":"2023-09-25","cited_by_count":5,"area":null},{"id":"2503.04372","title":"Assumed Identities: Quantifying Gender Bias in Machine Translation of Gender-Ambiguous Occupational Terms","created":"2025-03-06","cited_by_count":5,"area":null},{"id":"2207.13948","title":"An Interpretability Evaluation Benchmark for Pre-trained Language Models","created":"2022-07-28","cited_by_count":4,"area":null},{"id":"2501.18649","title":"Fake News Detection After LLM Laundering: Measurement and Explanation","created":"2025-01-29","cited_by_count":4,"area":null},{"id":"2101.11889","title":"Explaining Natural Language Processing Classifiers with Occlusion and Language Modeling","created":"2021-01-28","cited_by_count":2,"area":null},{"id":"2303.13850","title":"Towards Learning and Explaining Indirect Causal Effects in Neural Networks","created":"2023-03-24","cited_by_count":2,"area":null},{"id":"2308.08407","title":"Explainable AI for clinical risk prediction: a survey of concepts, methods, and modalities","created":"2023-08-16","cited_by_count":2,"area":null},{"id":"2311.07556","title":"Using Natural Language Explanations to Improve Robustness of In-context Learning","created":"2023-11-13","cited_by_count":2,"area":null},{"id":"2102.00854","title":"Hierarchical Variational Autoencoder for Visual Counterfactuals","created":"2021-02-01","cited_by_count":1,"area":null},{"id":"2106.06697","title":"Explaining the Deep Natural Language Processing by Mining Textual Interpretable Features","created":"2021-06-12","cited_by_count":1,"area":null},{"id":"2205.13342","title":"Leveraging Causal Inference for Explainable Automatic Program Repair","created":"2022-05-26","cited_by_count":1,"area":null},{"id":"2303.03019","title":"NxPlain: Web-based Tool for Discovery of Latent Concepts","created":"2023-03-06","cited_by_count":1,"area":null},{"id":"2411.16251","title":"Transparent Neighborhood Approximation for Text Classifier Explanation","created":"2024-11-25","cited_by_count":1,"area":null},{"id":"2503.16444","title":"Conversational Explanations: Discussing Explainable AI with Non-AI Experts","created":"2025-02-16","cited_by_count":1,"area":null},{"id":"2507.23399","title":"Beyond the Cloud: Assessing the Benefits and Drawbacks of Local LLM Deployment for Translators","created":"2025-07-31","cited_by_count":1,"area":null},{"id":"2104.08147","title":"Uncertainty Surrogates for Deep Learning","created":"2021-04-16","cited_by_count":0,"area":null},{"id":"2304.02625","title":"Towards Explainable AI Writing Assistants for Non-native English Speakers","created":"2023-04-05","cited_by_count":0,"area":null},{"id":"2305.03002","title":"Evaluating Post-hoc Interpretability with Intrinsic Interpretability","created":"2023-05-04","cited_by_count":0,"area":null},{"id":"2311.02345","title":"Perturbation-based Active Learning for Question Answering","created":"2023-11-04","cited_by_count":0,"area":null},{"id":"2311.13454","title":"Explaining high-dimensional text classifiers","created":"2023-11-22","cited_by_count":0,"area":null},{"id":"2406.11785","title":"CELL your Model: Contrastive Explanations for Large Language Models","created":"2024-06-17","cited_by_count":0,"area":null},{"id":"2505.09660","title":"On Measuring Intrinsic Causal Attributions in Deep Neural Networks","created":"2025-05-14","cited_by_count":0,"area":null}],"next_cursor":null}