{"total":38,"rows":[{"id":"2206.11104","title":"OpenXAI: Towards a Transparent Evaluation of Model Explanations","created":"2022-06-22","cited_by_count":126,"area":null},{"id":"2206.01254","title":"Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations","created":"2022-06-02","cited_by_count":77,"area":null},{"id":"2406.12232","title":"\"You Gotta be a Doctor, Lin\": An Investigation of Name-Based Bias of Large Language Models in Employment Recommendations","created":"2024-06-18","cited_by_count":33,"area":null},{"id":"2310.13007","title":"A Critical Survey on Fairness Benefits of Explainable AI","created":"2023-10-15","cited_by_count":16,"area":null},{"id":"2307.00364","title":"The future of human-centric eXplainable Artificial Intelligence (XAI) is not post-hoc explanations","created":"2023-07-01","cited_by_count":12,"area":null},{"id":"2402.12038","title":"Self-AMPLIFY: Improving Small Language Models with Self Post Hoc Explanations","created":"2024-02-19","cited_by_count":8,"area":null},{"id":"2505.10399","title":"Evaluating Model Explanations without Ground Truth","created":"2025-05-15","cited_by_count":7,"area":null},{"id":"2206.12481","title":"Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functions","created":"2022-06-24","cited_by_count":6,"area":null},{"id":"2311.07763","title":"The Disagreement Problem in Faithfulness Metrics","created":"2023-11-13","cited_by_count":6,"area":null},{"id":"2312.04542","title":"SoK: Unintended Interactions among Machine Learning Defenses and Risks","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2401.14539","title":"Understanding Disparities in Post Hoc Machine Learning Explanation","created":"2024-01-25","cited_by_count":6,"area":null},{"id":"2307.00660","title":"Minimum Levels of Interpretability for Artificial Moral Agents","created":"2023-07-02","cited_by_count":5,"area":null},{"id":"2406.11547","title":"GECOBench: A Gender-Controlled Text Dataset and Benchmark for Quantifying Biases in Explanations","created":"2024-06-17","cited_by_count":5,"area":null},{"id":"2504.07170","title":"Trustworthy AI Must Account for Interactions","created":"2025-04-09","cited_by_count":5,"area":null},{"id":"2311.17228","title":"Survey on AI Ethics: A Socio-technical Perspective","created":"2023-11-28","cited_by_count":4,"area":null},{"id":"2312.16191","title":"SoK: Taming the Triangle -- On the Interplays between Fairness, Interpretability and Privacy in Machine Learning","created":"2023-12-22","cited_by_count":4,"area":null},{"id":"2404.01877","title":"Procedural Fairness in Machine Learning","created":"2024-04-02","cited_by_count":4,"area":null},{"id":"2210.04491","title":"A survey of Identification and mitigation of Machine Learning algorithmic biases in Image Analysis","created":"2022-10-10","cited_by_count":3,"area":null},{"id":"2402.10762","title":"On Explaining Unfairness: An Overview","created":"2024-02-16","cited_by_count":3,"area":null},{"id":"2505.01198","title":"Gender Bias in Explainability: Investigating Performance Disparity in Post-hoc Methods","created":"2025-05-02","cited_by_count":3,"area":null},{"id":"2406.00116","title":"A Sim2Real Approach for Identifying Task-Relevant Properties in Interpretable Machine Learning","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2303.11111","title":"Iterative Partial Fulfillment of Counterfactual Explanations: Benefits and Risks","created":"2023-03-17","cited_by_count":1,"area":null},{"id":"2404.16495","title":"T-Explainer: A Model-Agnostic Explainability Framework Based on Gradients","created":"2024-04-25","cited_by_count":1,"area":null},{"id":"2407.00849","title":"Towards Understanding Sensitive and Decisive Patterns in Explainable AI: A Case Study of Model Interpretation in Geometric Deep Learning","created":"2024-06-30","cited_by_count":1,"area":null},{"id":"2502.20635","title":"Can LLM Assist in the Evaluation of the Quality of Machine Learning Explanations?","created":"2025-02-28","cited_by_count":1,"area":null},{"id":"2603.11140","title":"Procedural Fairness via Group Counterfactual Explanation","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2211.07650","title":"Explainer Divergence Scores (EDS): Some Post-Hoc Explanations May be Effective for Detecting Unknown Spurious Correlations","created":"2022-11-14","cited_by_count":0,"area":null},{"id":"2212.07508","title":"Tensions Between the Proxies of Human Values in AI","created":"2022-12-14","cited_by_count":0,"area":null},{"id":"2403.13848","title":"Smooth Sensitivity for Learning Differentially-Private yet Accurate Rule Lists","created":"2024-03-18","cited_by_count":0,"area":null},{"id":"2404.03426","title":"Accurate estimation of feature importance faithfulness for tree models","created":"2024-04-04","cited_by_count":0,"area":null},{"id":"2410.18560","title":"\"Let's Agree to Disagree\": Investigating the Disagreement Problem in Explainable AI for Text Summarization","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2502.02786","title":"When Machine Learning Gets Personal: Evaluating Prediction and Explanation","created":"2025-02-05","cited_by_count":0,"area":null},{"id":"2504.08919","title":"Are We Merely Justifying Results ex Post Facto? Quantifying Explanatory Inversion in Post-Hoc Model Explanations","created":"2025-04-11","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},{"id":"2605.08671","title":"Explanation Fairness in Large Language Models: An Empirical Analysis of Disparities in How LLMs Justify Decisions Across Demographic Groups","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.12701","title":"Do Fair Models Reason Fairly? Counterfactual Explanation Consistency for Procedural Fairness in Credit Decisions","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.15295","title":"GESD: Beyond Outcome-Oriented Fairness","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.28626","title":"When Interpretability Is Unequally Distributed: Fairness in Hybrid Interpretable Models","created":"2026-05-27","cited_by_count":0,"area":null}],"next_cursor":null}