{"total":126,"rows":[{"id":"2201.08164","title":"From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI","created":"2022-01-20","cited_by_count":302,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2104.14403","title":"Do Feature Attribution Methods Correctly Attribute Features?","created":"2021-04-27","cited_by_count":98,"area":null},{"id":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92,"area":null},{"id":"2106.00786","title":"The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations","created":"2021-06-01","cited_by_count":87,"area":null},{"id":"2111.08284","title":"Few-Shot Self-Rationalization with Natural Language Prompts","created":"2021-11-16","cited_by_count":83,"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":"2103.12279","title":"SelfExplain: A Self-Explaining Architecture for Neural Text Classifiers","created":"2021-03-23","cited_by_count":44,"area":null},{"id":"2306.02109","title":"Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency","created":"2023-06-03","cited_by_count":42,"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":"2206.11863","title":"CHEF: A Pilot Chinese Dataset for Evidence-Based Fact-Checking","created":"2022-06-06","cited_by_count":37,"area":null},{"id":"2110.13880","title":"Understanding Interlocking Dynamics of Cooperative Rationalization","created":"2021-10-26","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":"2309.17050","title":"Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models","created":"2023-09-29","cited_by_count":35,"area":"rag"},{"id":"2112.06837","title":"Sparse Interventions in Language Models with Differentiable Masking","created":"2021-12-13","cited_by_count":34,"area":null},{"id":"2112.08802","title":"UNIREX: A Unified Learning Framework for Language Model Rationale Extraction","created":"2021-12-16","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":"2101.04109","title":"Explain and Predict, and then Predict Again","created":"2021-01-11","cited_by_count":29,"area":null},{"id":"2105.02657","title":"Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification","created":"2021-05-06","cited_by_count":29,"area":null},{"id":"2109.06387","title":"Rationales for Sequential Predictions","created":"2021-09-14","cited_by_count":26,"area":null},{"id":"2112.00071","title":"What to Learn, and How: Toward Effective Learning from Rationales","created":"2021-11-30","cited_by_count":25,"area":null},{"id":"2407.19200","title":"On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs","created":"2024-07-27","cited_by_count":25,"area":"mechinterp"},{"id":"2106.13876","title":"Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations","created":"2021-06-25","cited_by_count":24,"area":null},{"id":"2305.17075","title":"CREST: A Joint Framework for Rationalization and Counterfactual Text Generation","created":"2023-05-26","cited_by_count":24,"area":null},{"id":"2406.01382","title":"Do Large Language Models Perform the Way People Expect? Measuring the Human Generalization Function","created":"2024-06-03","cited_by_count":24,"area":null},{"id":"2408.01416","title":"The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis","created":"2024-08-02","cited_by_count":24,"area":"mechinterp"},{"id":"2301.08912","title":"Rationalization for Explainable NLP: A Survey","created":"2023-01-21","cited_by_count":22,"area":null},{"id":"2310.12611","title":"Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model","created":"2023-10-19","cited_by_count":22,"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":"2203.00056","title":"An Empirical Study on Explanations in Out-of-Domain Settings","created":"2022-02-28","cited_by_count":21,"area":null},{"id":"2204.05426","title":"ProtoTEx: Explaining Model Decisions with Prototype Tensors","created":"2022-04-11","cited_by_count":21,"area":null},{"id":"2204.10810","title":"Learning to Scaffold: Optimizing Model Explanations for Teaching","created":"2022-04-22","cited_by_count":20,"area":null},{"id":"2105.04837","title":"Rationalization through Concepts","created":"2021-05-11","cited_by_count":19,"area":null},{"id":"2109.04552","title":"SPECTRA: Sparse Structured Text Rationalization","created":"2021-09-09","cited_by_count":19,"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":"2109.05463","title":"Logic Traps in Evaluating Attribution Scores","created":"2021-09-12","cited_by_count":18,"area":null},{"id":"2209.08285","title":"FR: Folded Rationalization with a Unified Encoder","created":"2022-09-17","cited_by_count":18,"area":null},{"id":"2210.07455","title":"Controlling Bias Exposure for Fair Interpretable Predictions","created":"2022-10-14","cited_by_count":18,"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":"2309.08395","title":"Learning by Self-Explaining","created":"2023-09-15","cited_by_count":17,"area":null},{"id":"2110.07550","title":"The Irrationality of Neural Rationale Models","created":"2021-10-14","cited_by_count":16,"area":null},{"id":"2305.06754","title":"COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP tasks","created":"2023-05-11","cited_by_count":16,"area":null},{"id":"2203.11131","title":"Towards Explainable Evaluation Metrics for Natural Language Generation","created":"2022-03-21","cited_by_count":15,"area":null},{"id":"2205.00130","title":"ExSum: From Local Explanations to Model Understanding","created":"2022-04-30","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":"2312.04103","title":"Enhancing the Rationale-Input Alignment for Self-explaining Rationalization","created":"2023-12-07","cited_by_count":15,"area":null},{"id":"2106.00320","title":"Distribution Matching for Rationalization","created":"2021-06-01","cited_by_count":14,"area":null},{"id":"2108.01988","title":"Sparse Continuous Distributions and Fenchel-Young Losses","created":"2021-08-04","cited_by_count":14,"area":null},{"id":"2210.03037","title":"Conversational Semantic Role Labeling with Predicate-Oriented Latent Graph","created":"2022-10-06","cited_by_count":14,"area":null},{"id":"2210.09197","title":"On the Impact of Temporal Concept Drift on Model Explanations","created":"2022-10-17","cited_by_count":14,"area":null},{"id":"2305.12962","title":"Distilling ChatGPT for Explainable Automated Student Answer Assessment","created":"2023-05-22","cited_by_count":14,"area":"distill"},{"id":"2305.13599","title":"Decoupled Rationalization with Asymmetric Learning Rates: A Flexible Lipschitz Restraint","created":"2023-05-23","cited_by_count":14,"area":null},{"id":"2402.13725","title":"Sparse and Structured Hopfield Networks","created":"2024-02-21","cited_by_count":13,"area":null},{"id":"2104.04488","title":"Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks","created":"2021-04-09","cited_by_count":12,"area":null},{"id":"2305.04492","title":"MGR: Multi-generator Based Rationalization","created":"2023-05-08","cited_by_count":12,"area":null},{"id":"2310.14805","title":"Cross-Modal Conceptualization in Bottleneck Models","created":"2023-10-23","cited_by_count":12,"area":null},{"id":"2402.00794","title":"ReAGent: A Model-agnostic Feature Attribution Method for Generative Language Models","created":"2024-02-01","cited_by_count":12,"area":null},{"id":"2112.10424","title":"Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction","created":"2021-12-20","cited_by_count":11,"area":null},{"id":"2104.08219","title":"Flexible Instance-Specific Rationalization of NLP Models","created":"2021-04-16","cited_by_count":10,"area":null},{"id":"2206.00759","title":"Interpretability Guarantees with Merlin-Arthur Classifiers","created":"2022-06-01","cited_by_count":9,"area":null},{"id":"2402.02933","title":"Intrinsic User-Centric Interpretability through Global Mixture of Experts","created":"2024-02-05","cited_by_count":9,"area":"moe"},{"id":"2106.00479","title":"DoT: An efficient Double Transformer for NLP tasks with tables","created":"2021-06-01","cited_by_count":8,"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":"2403.07955","title":"Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery","created":"2024-03-12","cited_by_count":8,"area":null},{"id":"2104.08793","title":"SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning","created":"2021-04-18","cited_by_count":7,"area":null},{"id":"2210.07440","title":"InterFair: Debiasing with Natural Language Feedback for Fair Interpretable Predictions","created":"2022-10-14","cited_by_count":7,"area":"alignment"},{"id":"2109.03756","title":"Diagnostics-Guided Explanation Generation","created":"2021-09-08","cited_by_count":6,"area":null},{"id":"2210.11318","title":"A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculture","created":"2022-10-20","cited_by_count":6,"area":null},{"id":"2305.03503","title":"Think Rationally about What You See: Continuous Rationale Extraction for Relation Extraction","created":"2023-05-02","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":"2109.08382","title":"To be Closer: Learning to Link up Aspects with Opinions","created":"2021-09-17","cited_by_count":5,"area":null},{"id":"2110.02056","title":"Are Training Resources Insufficient? Predict First Then Explain!","created":"2021-08-29","cited_by_count":5,"area":null},{"id":"2202.09792","title":"Hierarchical Interpretation of Neural Text Classification","created":"2022-02-20","cited_by_count":5,"area":null},{"id":"2204.11424","title":"It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers","created":"2022-04-25","cited_by_count":5,"area":null},{"id":"2205.02684","title":"RaFoLa: A Rationale-Annotated Corpus for Detecting Indicators of Forced Labour","created":"2022-05-05","cited_by_count":5,"area":null},{"id":"2305.14237","title":"HOP, UNION, GENERATE: Explainable Multi-hop Reasoning without Rationale Supervision","created":"2023-05-23","cited_by_count":5,"area":"lr"},{"id":"2402.09702","title":"Sparse and Faithful Explanations Without Sparse Models","created":"2024-02-15","cited_by_count":5,"area":null},{"id":"2404.03098","title":"Exploring the Trade-off Between Model Performance and Explanation Plausibility of Text Classifiers Using Human Rationales","created":"2024-04-03","cited_by_count":5,"area":null},{"id":"2407.19471","title":"On the Evaluation Consistency of Attribution-based Explanations","created":"2024-07-28","cited_by_count":5,"area":null},{"id":"2508.08274","title":"Distilling Knowledge from Large Language Models: A Concept Bottleneck Model for Hate and Counter Speech Recognition","created":"2025-07-30","cited_by_count":5,"area":null},{"id":"2602.04541","title":"LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding","created":"2026-02-04","cited_by_count":5,"area":"inference"},{"id":"2105.06982","title":"EASE: Extractive-Abstractive Summarization with Explanations","created":"2021-05-14","cited_by_count":4,"area":null},{"id":"2106.12920","title":"Learnt Sparsification for Interpretable Graph Neural Networks","created":"2021-06-23","cited_by_count":4,"area":null},{"id":"2110.10144","title":"FaxPlainAC: A Fact-Checking Tool Based on EXPLAINable Models with HumAn Correction in the Loop","created":"2021-09-12","cited_by_count":4,"area":null},{"id":"2203.01146","title":"Controlling the Focus of Pretrained Language Generation Models","created":"2022-03-02","cited_by_count":4,"area":null},{"id":"2301.06009","title":"Rationalizing Predictions by Adversarial Information Calibration","created":"2023-01-15","cited_by_count":4,"area":null},{"id":"2301.08914","title":"ExClaim: Explainable Neural Claim Verification Using Rationalization","created":"2023-01-21","cited_by_count":4,"area":null},{"id":"2304.06391","title":"VISION DIFFMASK: Faithful Interpretation of Vision Transformers with Differentiable Patch Masking","created":"2023-04-13","cited_by_count":4,"area":"mechinterp"},{"id":"2305.16128","title":"Give Me More Details: Improving Fact-Checking with Latent Retrieval","created":"2023-05-25","cited_by_count":4,"area":null},{"id":"2410.03531","title":"MARE: Multi-Aspect Rationale Extractor on Unsupervised Rationale Extraction","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2502.13991","title":"Learning to Discover Regulatory Elements for Gene Expression Prediction","created":"2025-02-19","cited_by_count":4,"area":null},{"id":"2504.02911","title":"Noiser: Bounded Input Perturbations for Attributing Large Language Models","created":"2025-04-03","cited_by_count":4,"area":null},{"id":"2111.07611","title":"Rationale production to support clinical decision-making","created":"2021-11-15","cited_by_count":3,"area":null},{"id":"2111.09029","title":"Towards Interpretable and Reliable Reading Comprehension: A Pipeline Model with Unanswerability Prediction","created":"2021-11-17","cited_by_count":3,"area":null},{"id":"2305.17534","title":"Unsupervised Selective Rationalization with Noise Injection","created":"2023-05-27","cited_by_count":3,"area":null},{"id":"2103.14919","title":"You Can Do Better! If You Elaborate the Reason When Making Prediction","created":"2021-03-27","cited_by_count":2,"area":null},{"id":"2108.02658","title":"Sparse Communication via Mixed Distributions","created":"2021-08-05","cited_by_count":2,"area":null},{"id":"2201.00490","title":"Learning with Latent Structures in Natural Language Processing: A Survey","created":"2022-01-03","cited_by_count":2,"area":null}],"next_cursor":"100"}