{"total":62,"rows":[{"id":"2409.02977","title":"Large Language Model-Based Agents for Software Engineering: A Survey","created":"2024-09-04","cited_by_count":178,"area":"agents"},{"id":"2404.04834","title":"LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead","created":"2024-04-07","cited_by_count":155,"area":"agents"},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2305.06969","title":"A Survey on Intersectional Fairness in Machine Learning: Notions, Mitigation, and Challenges","created":"2023-05-11","cited_by_count":41,"area":null},{"id":"2305.11602","title":"Latent Imitator: Generating Natural Individual Discriminatory Instances for Black-Box Fairness Testing","created":"2023-05-19","cited_by_count":23,"area":null},{"id":"2401.00763","title":"New Job, New Gender? Measuring the Social Bias in Image Generation Models","created":"2024-01-01","cited_by_count":16,"area":null},{"id":"2302.08018","title":"Towards Fair Machine Learning Software: Understanding and Addressing Model Bias Through Counterfactual Thinking","created":"2023-02-16","cited_by_count":14,"area":null},{"id":"2411.00585","title":"Fairness Testing of Large Language Models in Role-Playing","created":"2024-11-01","cited_by_count":11,"area":null},{"id":"2305.02626","title":"\"Oops, Did I Just Say That?\" Testing and Repairing Unethical Suggestions of Large Language Models with Suggest-Critique-Reflect Process","created":"2023-05-04","cited_by_count":9,"area":null},{"id":"2404.05388","title":"An AI System Evaluation Framework for Advancing AI Safety: Terminology, Taxonomy, Lifecycle Mapping","created":"2024-04-08","cited_by_count":8,"area":null},{"id":"2308.02935","title":"Bias Behind the Wheel: Fairness Testing of Autonomous Driving Systems","created":"2023-08-05","cited_by_count":7,"area":null},{"id":"2401.03695","title":"A Large-Scale Empirical Study on Improving the Fairness of Image Classification Models","created":"2024-01-08","cited_by_count":6,"area":null},{"id":"2505.19562","title":"FairMedQA: Benchmarking Bias in Large Language Models for Medical Question Answering","created":"2025-05-26","cited_by_count":6,"area":null},{"id":"2403.20089","title":"Implications of the AI Act for Non-Discrimination Law and Algorithmic Fairness","created":"2024-03-29","cited_by_count":5,"area":null},{"id":"2505.07997","title":"FairZK: A Scalable System to Prove Machine Learning Fairness in Zero-Knowledge","created":"2025-05-12","cited_by_count":5,"area":null},{"id":"2401.08097","title":"Fairness Concerns in App Reviews: A Study on AI-based Mobile Apps","created":"2024-01-16","cited_by_count":4,"area":null},{"id":"2401.12720","title":"A Comprehensive View of the Biases of Toxicity and Sentiment Analysis Methods Towards Utterances with African American English Expressions","created":"2024-01-23","cited_by_count":4,"area":null},{"id":"2501.15775","title":"Do Existing Testing Tools Really Uncover Gender Bias in Text-to-Image Models?","created":"2025-01-27","cited_by_count":4,"area":"diffusion"},{"id":"2304.07030","title":"FairRec: Fairness Testing for Deep Recommender Systems","created":"2023-04-14","cited_by_count":3,"area":null},{"id":"2309.11691","title":"RAI4IoE: Responsible AI for Enabling the Internet of Energy","created":"2023-09-20","cited_by_count":3,"area":null},{"id":"2412.08167","title":"Diversity Drives Fairness: Ensemble of Higher Order Mutants for Intersectional Fairness of Machine Learning Software","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2508.19882","title":"Generative AI for Testing of Autonomous Driving Systems: A Survey","created":"2025-08-27","cited_by_count":3,"area":null},{"id":"2209.08321","title":"Enhanced Fairness Testing via Generating Effective Initial Individual Discriminatory Instances","created":"2022-09-17","cited_by_count":2,"area":null},{"id":"2405.13693","title":"Mutatis Mutandis: Revisiting the Comparator in Discrimination Testing","created":"2024-05-22","cited_by_count":2,"area":null},{"id":"2502.01267","title":"Counterfactual Situation Testing: From Single to Multidimensional Discrimination","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2509.13803","title":"Measuring Gender Bias in Job Title Matching for Grammatical Gender Languages","created":"2025-09-17","cited_by_count":2,"area":null},{"id":"2512.23745","title":"A Comprehensive Study of Deep Learning Model Fixing Approaches","created":"2025-12-26","cited_by_count":2,"area":null},{"id":"2302.01574","title":"An Operational Perspective to Fairness Interventions: Where and How to Intervene","created":"2023-02-03","cited_by_count":1,"area":null},{"id":"2307.11379","title":"Towards Better Fairness-Utility Trade-off: A Comprehensive Measurement-Based Reinforcement Learning Framework","created":"2023-07-21","cited_by_count":1,"area":null},{"id":"2404.18736","title":"Mapping the Potential of Explainable AI for Fairness Along the AI Lifecycle","created":"2024-04-29","cited_by_count":1,"area":null},{"id":"2406.17906","title":"Unbiasing on the Fly: Explanation-Guided Human Oversight of Machine Learning System Decisions","created":"2024-06-25","cited_by_count":1,"area":null},{"id":"2410.06423","title":"FAIREDU: A Multiple Regression-Based Method for Enhancing Fairness in Machine Learning Models for Educational Applications","created":"2024-10-08","cited_by_count":1,"area":null},{"id":"2504.12587","title":"Software Engineering Principles for Fairer Systems: Experiments with GroupCART","created":"2025-04-17","cited_by_count":1,"area":null},{"id":"2505.00830","title":"Intersectional Divergence: Measuring Fairness in Regression","created":"2025-05-01","cited_by_count":1,"area":null},{"id":"2505.11132","title":"Fairness-aware Anomaly Detection via Fair Projection","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2508.03323","title":"Software Fairness Dilemma: Is Bias Mitigation a Zero-Sum Game?","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2509.26166","title":"Beyond Overall Accuracy: Pose- and Occlusion-driven Fairness Analysis in Pedestrian Detection for Autonomous Driving","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2509.26584","title":"Fairness Testing in Retrieval-Augmented Generation: How Small Perturbations Reveal Bias in Small Language Models","created":"2025-09-30","cited_by_count":1,"area":"rag"},{"id":"2510.18719","title":"Causally Perturbed Fairness Testing","created":"2025-10-21","cited_by_count":1,"area":null},{"id":"2305.13935","title":"Distribution-aware Fairness Test Generation","created":"2023-05-08","cited_by_count":0,"area":null},{"id":"2308.01923","title":"Fairness Improvement with Multiple Protected Attributes: How Far Are We?","created":"2023-07-25","cited_by_count":0,"area":null},{"id":"2311.06175","title":"Search-Based Fairness Testing: An Overview","created":"2023-11-10","cited_by_count":0,"area":null},{"id":"2407.01595","title":"Fairpriori: Improving Biased Subgroup Discovery for Deep Neural Network Fairness","created":"2024-06-25","cited_by_count":0,"area":null},{"id":"2408.06102","title":"Contexts Matter: An Empirical Study on Contextual Influence in Fairness Testing for Deep Learning Systems","created":"2024-08-12","cited_by_count":0,"area":null},{"id":"2503.16740","title":"Automated Harmfulness Testing for Code Large Language Models","created":"2025-03-20","cited_by_count":0,"area":"safety"},{"id":"2504.17066","title":"Whence Is A Model Fair? Fixing Fairness Bugs via Propensity Score Matching","created":"2025-04-23","cited_by_count":0,"area":null},{"id":"2504.18353","title":"Testing Individual Fairness in Graph Neural Networks","created":"2025-04-25","cited_by_count":0,"area":null},{"id":"2507.04033","title":"Benchmarking Stochastic Approximation Algorithms for Fairness-Constrained Training of Deep Neural Networks","created":"2025-07-05","cited_by_count":0,"area":null},{"id":"2508.08151","title":"FairFLRep: Fairness aware fault localization and repair of Deep Neural Networks","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2509.16525","title":"CAF\\'E: Causal Black-Box Testing of Machine Unlearning","created":"2025-09-20","cited_by_count":0,"area":"safety"},{"id":"2510.04114","title":"Wasserstein projection distance for fairness testing of regression models","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2512.07990","title":"A Gray Literature Study on Fairness Requirements in AI-enabled Software Engineering","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2512.21348","title":"Fairness Is Not Just Ethical: Performance Trade-Off via Data Correlation Tuning to Mitigate Bias in ML Software","created":"2025-12-19","cited_by_count":0,"area":null},{"id":"2602.05833","title":"SecretFan: Synthesizing Realistic Data without Breaking Privacy","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2603.21393","title":"A Generalised Exponentiated Gradient Approach to Enhance Fairness in Binary and Multi-class Classification Tasks","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2604.16536","title":"Towards Reliable Testing of Machine Unlearning","created":"2026-04-16","cited_by_count":0,"area":"safety"},{"id":"2604.20677","title":"Intersectional Fairness in Large Language Models","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2604.22089","title":"Ethics Testing: Proactive Identification of Generative AI System Harms","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2605.19549","title":"Provable Fairness Repair for Deep Neural Networks","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.27960","title":"Reasoning Beyond Prediction: From Data-Driven to Causal Software Engineering","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.12863","title":"Toward Localizing and Repairing Bias in Transformer Attention Heads","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2608.23893","title":"Provenance Guided Incremental Learning Under Evolving Concept Definitions","created":"2026-08-24","cited_by_count":0,"area":null}],"next_cursor":null}