{"total":54,"rows":[{"id":"2111.14338","title":"Improving Deep Learning Interpretability by Saliency Guided Training","created":"2021-11-29","cited_by_count":68,"area":null},{"id":"2401.12874","title":"From Understanding to Utilization: A Survey on Explainability for Large Language Models","created":"2024-01-23","cited_by_count":48,"area":null},{"id":"2205.03286","title":"GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers","created":"2022-05-06","cited_by_count":44,"area":null},{"id":"2105.03287","title":"Order in the Court: Explainable AI Methods Prone to Disagreement","created":"2021-05-07","cited_by_count":36,"area":null},{"id":"2306.02873","title":"DecompX: Explaining Transformers Decisions by Propagating Token Decomposition","created":"2023-06-05","cited_by_count":31,"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":"2106.10649","title":"CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliency","created":"2021-06-20","cited_by_count":28,"area":null},{"id":"2410.09087","title":"Mechanistic?","created":"2024-10-07","cited_by_count":25,"area":"mechinterp"},{"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":"2105.10912","title":"CiteWorth: Cite-Worthiness Detection for Improved Scientific Document Understanding","created":"2021-05-23","cited_by_count":17,"area":null},{"id":"2309.07822","title":"CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration","created":"2023-09-14","cited_by_count":17,"area":null},{"id":"2108.13759","title":"Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience","created":"2021-08-31","cited_by_count":16,"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":"2305.10496","title":"Incorporating Attribution Importance for Improving Faithfulness Metrics","created":"2023-05-17","cited_by_count":14,"area":"lr"},{"id":"2205.04559","title":"A Song of (Dis)agreement: Evaluating the Evaluation of Explainable Artificial Intelligence in Natural Language Processing","created":"2022-05-09","cited_by_count":13,"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":"2104.08219","title":"Flexible Instance-Specific Rationalization of NLP Models","created":"2021-04-16","cited_by_count":10,"area":null},{"id":"2310.00772","title":"SMOOT: Saliency Guided Mask Optimized Online Training","created":"2023-10-01","cited_by_count":8,"area":null},{"id":"2401.13335","title":"Full Bayesian Significance Testing for Neural Networks","created":"2024-01-24","cited_by_count":8,"area":null},{"id":"2112.04934","title":"Model Doctor: A Simple Gradient Aggregation Strategy for Diagnosing and Treating CNN Classifiers","created":"2021-12-09","cited_by_count":6,"area":null},{"id":"2210.08500","title":"This Patient Looks Like That Patient: Prototypical Networks for Interpretable Diagnosis Prediction from Clinical Text","created":"2022-10-16","cited_by_count":6,"area":null},{"id":"2403.12809","title":"Comparing Explanation Faithfulness between Multilingual and Monolingual Fine-tuned Language Models","created":"2024-03-19","cited_by_count":6,"area":null},{"id":"2406.12649","title":"Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation Models","created":"2024-06-18","cited_by_count":6,"area":null},{"id":"2204.10080","title":"Identifying and Characterizing Active Citizens who Refute Misinformation in Social Media","created":"2022-04-21","cited_by_count":5,"area":null},{"id":"2310.07819","title":"Faithfulness Measurable Masked Language Models","created":"2023-10-11","cited_by_count":5,"area":null},{"id":"2411.05858","title":"Saliency Assisted Quantization for Neural Networks","created":"2024-11-07","cited_by_count":5,"area":null},{"id":"2411.16760","title":"LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions","created":"2024-11-24","cited_by_count":5,"area":null},{"id":"2204.09498","title":"Backdooring Explainable Machine Learning","created":"2022-04-20","cited_by_count":4,"area":null},{"id":"2312.17591","title":"Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training","created":"2023-12-29","cited_by_count":4,"area":null},{"id":"2403.10831","title":"DUE: Dynamic Uncertainty-Aware Explanation Supervision via 3D Imputation","created":"2024-03-16","cited_by_count":4,"area":null},{"id":"2411.16252","title":"NormXLogit: The Head-on-Top Never Lies","created":"2024-11-25","cited_by_count":4,"area":null},{"id":"2412.03915","title":"Quantized and Interpretable Learning Scheme for Deep Neural Networks in Classification Task","created":"2024-12-05","cited_by_count":4,"area":null},{"id":"2502.12992","title":"B-cos LM: Efficiently Transforming Pre-trained Language Models for Improved Explainability","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2109.00222","title":"Spatio-Temporal Perturbations for Video Attribution","created":"2021-09-01","cited_by_count":3,"area":null},{"id":"2207.11290","title":"TRUST-LAPSE: An Explainable and Actionable Mistrust Scoring Framework for Model Monitoring","created":"2022-07-22","cited_by_count":3,"area":null},{"id":"2210.03683","title":"Quantitative Metrics for Evaluating Explanations of Video DeepFake Detectors","created":"2022-10-07","cited_by_count":3,"area":null},{"id":"2211.08425","title":"A Rigorous Study Of The Deep Taylor Decomposition","created":"2022-11-14","cited_by_count":3,"area":null},{"id":"2311.00189","title":"XAI-CLASS: Explanation-Enhanced Text Classification with Extremely Weak Supervision","created":"2023-10-31","cited_by_count":3,"area":null},{"id":"2406.17792","title":"Applications of interpretable deep learning in neuroimaging: a comprehensive review","created":"2024-05-30","cited_by_count":3,"area":null},{"id":"2302.02852","title":"Guide the Learner: Controlling Product of Experts Debiasing Method Based on Token Attribution Similarities","created":"2023-02-06","cited_by_count":2,"area":null},{"id":"2303.17836","title":"Rethinking interpretation: Input-agnostic saliency mapping of deep visual classifiers","created":"2023-03-31","cited_by_count":2,"area":null},{"id":"2102.12354","title":"On the Impact of Interpretability Methods in Active Image Augmentation Method","created":"2021-02-24","cited_by_count":1,"area":null},{"id":"2407.16693","title":"Explanation Regularisation through the Lens of Attributions","created":"2024-07-23","cited_by_count":1,"area":null},{"id":"2102.07332","title":"Attribution Mask: Filtering Out Irrelevant Features By Recursively Focusing Attention on Inputs of DNNs","created":"2021-02-15","cited_by_count":0,"area":null},{"id":"2106.10086","title":"It's FLAN time! Summing feature-wise latent representations for interpretability","created":"2021-06-18","cited_by_count":0,"area":null},{"id":"2111.05108","title":"\"How Does It Detect A Malicious App?\" Explaining the Predictions of AI-based Android Malware Detector","created":"2021-11-06","cited_by_count":0,"area":null},{"id":"2211.04946","title":"Accountable and Explainable Methods for Complex Reasoning over Text","created":"2022-11-09","cited_by_count":0,"area":null},{"id":"2305.03508","title":"CiteCaseLAW: Citation Worthiness Detection in Caselaw for Legal Assistive Writing","created":"2023-05-03","cited_by_count":0,"area":null},{"id":"2305.07988","title":"Reconstruct Before Summarize: An Efficient Two-Step Framework for Condensing and Summarizing Meeting Transcripts","created":"2023-05-13","cited_by_count":0,"area":null},{"id":"2402.07506","title":"NeuralSentinel: Safeguarding Neural Network Reliability and Trustworthiness","created":"2024-02-12","cited_by_count":0,"area":null},{"id":"2403.08428","title":"DeepCSHAP: Utilizing Shapley Values to Explain Deep Complex-Valued Neural Networks","created":"2024-03-13","cited_by_count":0,"area":null},{"id":"2509.22291","title":"Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2511.19719","title":"Can LLMs Faithfully Explain Themselves in Low-Resource Languages? A Case Study on Emotion Detection in Persian","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2601.12419","title":"Legal Experts Disagree With Rationale Extraction Techniques for Explaining ECtHR Case Outcome Classification","created":"2026-01-18","cited_by_count":0,"area":null}],"next_cursor":null}