{"total":22,"rows":[{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639,"area":null},{"id":"2403.19647","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","created":"2024-03-28","cited_by_count":435,"area":null},{"id":"2308.10149","title":"A Survey on Fairness in Large Language Models","created":"2023-08-20","cited_by_count":95,"area":null},{"id":"2306.08158","title":"Sociodemographic Bias in Language Models: A Survey and Forward Path","created":"2023-06-13","cited_by_count":28,"area":null},{"id":"2406.05392","title":"Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey","created":"2024-06-08","cited_by_count":23,"area":null},{"id":"2406.04755","title":"LLM Whisperer: An Inconspicuous Attack to Bias LLM Responses","created":"2024-06-07","cited_by_count":15,"area":null},{"id":"2501.14457","title":"Understanding and Mitigating Gender Bias in LLMs via Interpretable Neuron Editing","created":"2025-01-24","cited_by_count":14,"area":null},{"id":"2312.01509","title":"Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societies","created":"2023-12-03","cited_by_count":11,"area":null},{"id":"2310.16607","title":"On the Interplay between Fairness and Explainability","created":"2023-10-25","cited_by_count":7,"area":null},{"id":"2503.15815","title":"Attention Pruning: Automated Fairness Repair of Language Models via Surrogate Simulated Annealing","created":"2025-03-20","cited_by_count":5,"area":null},{"id":"2406.05918","title":"Why Don't Prompt-Based Fairness Metrics Correlate?","created":"2024-06-09","cited_by_count":4,"area":null},{"id":"2506.04652","title":"EMO-Debias: Benchmarking Gender Debiasing Techniques in Multi-Label Speech Emotion Recognition","created":"2025-06-05","cited_by_count":3,"area":null},{"id":"2404.18276","title":"Bias Neutralization Framework: Measuring Fairness in Large Language Models with Bias Intelligence Quotient (BiQ)","created":"2024-04-28","cited_by_count":1,"area":null},{"id":"2506.06071","title":"CO-VADA: A Confidence-Oriented Voice Augmentation Debiasing Approach for Fair Speech Emotion Recognition","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2506.11244","title":"Iterative Multilingual Spectral Attribute Erasure","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2305.12671","title":"Transferring Fairness using Multi-Task Learning with Limited Demographic Information","created":"2023-05-22","cited_by_count":0,"area":null},{"id":"2411.15051","title":"Fantastic Biases (What are They) and Where to Find Them","created":"2024-11-22","cited_by_count":0,"area":null},{"id":"2503.19426","title":"DeCAP: Context-Adaptive Prompt Generation for Debiasing Zero-shot Question Answering in Large Language Models","created":"2025-03-25","cited_by_count":0,"area":null},{"id":"2508.03677","title":"FairLangProc: A Python package for fairness in NLP","created":"2025-08-05","cited_by_count":0,"area":null},{"id":"2509.15206","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2606.12088","title":"Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2608.29257","title":"Large Language Models Systematically Favor Popular Options: Evidence and Mitigation Across MCQs","created":"2026-08-29","cited_by_count":0,"area":null}],"next_cursor":null}