{"total":73,"rows":[{"id":"2205.09209","title":"\"I'm sorry to hear that\": Finding New Biases in Language Models with a Holistic Descriptor Dataset","created":"2022-05-18","cited_by_count":162,"area":null},{"id":"2305.14456","title":"Having Beer after Prayer? Measuring Cultural Bias in Large Language Models","created":"2023-05-23","cited_by_count":153,"area":null},{"id":"2309.12342","title":"Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions","created":"2023-08-25","cited_by_count":112,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2205.02894","title":"Interactive Model Cards: A Human-Centered Approach to Model Documentation","created":"2022-05-05","cited_by_count":61,"area":null},{"id":"2302.02463","title":"Nationality Bias in Text Generation","created":"2023-02-05","cited_by_count":50,"area":null},{"id":"2210.07626","title":"BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation","created":"2022-10-14","cited_by_count":48,"area":null},{"id":"2306.15087","title":"WinoQueer: A Community-in-the-Loop Benchmark for Anti-LGBTQ+ Bias in Large Language Models","created":"2023-06-26","cited_by_count":42,"area":null},{"id":"2108.01250","title":"Your fairness may vary: Pretrained language model fairness in toxic text classification","created":"2021-08-03","cited_by_count":39,"area":null},{"id":"2305.11242","title":"Comparing Biases and the Impact of Multilingual Training across Multiple Languages","created":"2023-05-18","cited_by_count":36,"area":null},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2309.08902","title":"Investigating Subtler Biases in LLMs: Ageism, Beauty, Institutional, and Nationality Bias in Generative Models","created":"2023-09-16","cited_by_count":32,"area":null},{"id":"2311.09090","title":"Social Bias Probing: Fairness Benchmarking for Language Models","created":"2023-11-15","cited_by_count":32,"area":null},{"id":"2210.10040","title":"The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarks","created":"2022-10-18","cited_by_count":31,"area":null},{"id":"2304.10153","title":"On the Independence of Association Bias and Empirical Fairness in Language Models","created":"2023-04-20","cited_by_count":29,"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":"2311.18580","title":"FFT: Towards Harmlessness Evaluation and Analysis for LLMs with Factuality, Fairness, Toxicity","created":"2023-11-30","cited_by_count":25,"area":null},{"id":"2402.17954","title":"Twists, Humps, and Pebbles: Multilingual Speech Recognition Models Exhibit Gender Performance Gaps","created":"2024-02-28","cited_by_count":25,"area":null},{"id":"2203.09866","title":"Under the Morphosyntactic Lens: A Multifaceted Evaluation of Gender Bias in Speech Translation","created":"2022-03-18","cited_by_count":23,"area":null},{"id":"2501.04437","title":"Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directions","created":"2025-01-08","cited_by_count":23,"area":null},{"id":"2206.03945","title":"Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models","created":"2022-06-08","cited_by_count":20,"area":null},{"id":"2307.09209","title":"Automated Ableism: An Exploration of Explicit Disability Biases in Sentiment and Toxicity Analysis Models","created":"2023-07-18","cited_by_count":20,"area":null},{"id":"2210.02015","title":"Conformalized Fairness via Quantile Regression","created":"2022-10-05","cited_by_count":19,"area":null},{"id":"2401.10535","title":"The \"Colonial Impulse\" of Natural Language Processing: An Audit of Bengali Sentiment Analysis Tools and Their Identity-based Biases","created":"2024-01-19","cited_by_count":16,"area":null},{"id":"2308.12539","title":"CALM : A Multi-task Benchmark for Comprehensive Assessment of Language Model Bias","created":"2023-08-24","cited_by_count":14,"area":null},{"id":"2403.10776","title":"From Melting Pots to Misrepresentations: Exploring Harms in Generative AI","created":"2024-03-16","cited_by_count":13,"area":null},{"id":"2407.05740","title":"Do Multilingual Large Language Models Mitigate Stereotype Bias?","created":"2024-07-08","cited_by_count":13,"area":null},{"id":"2305.16577","title":"Nichelle and Nancy: The Influence of Demographic Attributes and Tokenization Length on First Name Biases","created":"2023-05-26","cited_by_count":12,"area":null},{"id":"2201.00768","title":"Robust Natural Language Processing: Recent Advances, Challenges, and Future Directions","created":"2022-01-03","cited_by_count":11,"area":null},{"id":"2410.10995","title":"Watching the Watchers: Exposing Gender Disparities in Machine Translation Quality Estimation","created":"2024-10-14","cited_by_count":10,"area":null},{"id":"2305.11348","title":"In the Name of Fairness: Assessing the Bias in Clinical Record De-identification","created":"2023-05-18","cited_by_count":9,"area":null},{"id":"2305.12757","title":"This Prompt is Measuring <MASK>: Evaluating Bias Evaluation in Language Models","created":"2023-05-22","cited_by_count":9,"area":null},{"id":"2206.11484","title":"Towards WinoQueer: Developing a Benchmark for Anti-Queer Bias in Large Language Models","created":"2022-06-23","cited_by_count":8,"area":null},{"id":"2205.04505","title":"Behind the Mask: Demographic bias in name detection for PII masking","created":"2022-05-09","cited_by_count":7,"area":null},{"id":"2212.11672","title":"Trustworthy Social Bias Measurement","created":"2022-12-20","cited_by_count":7,"area":null},{"id":"2306.04735","title":"Soft-prompt Tuning for Large Language Models to Evaluate Bias","created":"2023-06-07","cited_by_count":7,"area":null},{"id":"2205.09867","title":"Gender Bias in Meta-Embeddings","created":"2022-05-19","cited_by_count":6,"area":null},{"id":"2210.10689","title":"Towards Procedural Fairness: Uncovering Biases in How a Toxic Language Classifier Uses Sentiment Information","created":"2022-10-19","cited_by_count":6,"area":null},{"id":"2410.15467","title":"Hey GPT, Can You be More Racist? Analysis from Crowdsourced Attempts to Elicit Biased Content from Generative AI","created":"2024-10-20","cited_by_count":6,"area":null},{"id":"2204.05459","title":"Easy Adaptation to Mitigate Gender Bias in Multilingual Text Classification","created":"2022-04-12","cited_by_count":5,"area":null},{"id":"2305.09281","title":"On the Origins of Bias in NLP through the Lens of the Jim Code","created":"2023-05-16","cited_by_count":5,"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":"2212.12799","title":"A Comprehensive Study of Gender Bias in Chemical Named Entity Recognition Models","created":"2022-12-24","cited_by_count":4,"area":null},{"id":"2309.14146","title":"Examining Temporal Bias in Abusive Language Detection","created":"2023-09-25","cited_by_count":4,"area":null},{"id":"2402.04420","title":"Measuring Machine Learning Harms from Stereotypes Requires Understanding Who Is Harmed by Which Errors in What Ways","created":"2024-02-06","cited_by_count":4,"area":null},{"id":"2403.05975","title":"Measuring Bias in a Ranked List using Term-based Representations","created":"2024-03-09","cited_by_count":4,"area":null},{"id":"2404.00463","title":"Addressing Both Statistical and Causal Gender Fairness in NLP Models","created":"2024-03-30","cited_by_count":4,"area":null},{"id":"2405.01790","title":"Understanding Position Bias Effects on Fairness in Social Multi-Document Summarization","created":"2024-05-03","cited_by_count":4,"area":null},{"id":"2407.01834","title":"A Study of Nationality Bias in Names and Perplexity using Off-the-Shelf Affect-related Tweet Classifiers","created":"2024-07-01","cited_by_count":4,"area":null},{"id":"2410.18749","title":"Does Differential Privacy Impact Bias in Pretrained NLP Models?","created":"2024-10-24","cited_by_count":2,"area":null},{"id":"2508.20201","title":"Social Bias in Multilingual Language Models: A Survey","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2510.11222","title":"Fairness Metric Design Exploration in Multi-Domain Moral Sentiment Classification using Transformer-Based Models","created":"2025-10-13","cited_by_count":2,"area":null},{"id":"2511.10089","title":"T2IBias: Uncovering Societal Bias Encoded in the Latent Space of Text-to-Image Generative Models","created":"2025-11-13","cited_by_count":2,"area":null},{"id":"2603.10001","title":"Leveraging Wikidata for Geographically Informed Sociocultural Bias Dataset Creation: Application to Latin America","created":"2026-02-16","cited_by_count":2,"area":null},{"id":"2402.11710","title":"A Note on Bias to Complete","created":"2024-02-18","cited_by_count":1,"area":null},{"id":"2404.03471","title":"Template-Based Probes Are Imperfect Lenses for Counterfactual Bias Evaluation in LLMs","created":"2024-04-04","cited_by_count":1,"area":null},{"id":"2505.18942","title":"Language Models Should be Used to Surface the Unwritten Code of Science and Society","created":"2025-05-25","cited_by_count":1,"area":null},{"id":"2506.22481","title":"Theories of \"Sexuality\" in Natural Language Processing Bias Research","created":"2025-06-22","cited_by_count":1,"area":null},{"id":"2310.18458","title":"Do Not Harm Protected Groups in Debiasing Language Representation Models","created":"2023-10-27","cited_by_count":0,"area":null},{"id":"2311.06513","title":"Step by Step to Fairness: Attributing Societal Bias in Task-oriented Dialogue Systems","created":"2023-11-11","cited_by_count":0,"area":null},{"id":"2402.18797","title":"ARTiST: Automated Text Simplification for Task Guidance in Augmented Reality","created":"2024-02-29","cited_by_count":0,"area":null},{"id":"2406.07229","title":"Improving Commonsense Bias Classification by Mitigating the Influence of Demographic Terms","created":"2024-06-11","cited_by_count":0,"area":null},{"id":"2410.03996","title":"On the Influence of Gender and Race in Romantic Relationship Prediction from Large Language Models","created":"2024-10-05","cited_by_count":0,"area":null},{"id":"2506.02321","title":"Quantifying Misattribution Unfairness in Authorship Attribution","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2506.06816","title":"How do datasets, developers, and models affect biases in a low-resourced language?: The Case of the Bengali Language","created":"2025-06-07","cited_by_count":0,"area":null},{"id":"2510.20508","title":"Assessing the Political Fairness of Multilingual LLMs: A Case Study based on a 21-way Multiparallel EuroParl Dataset","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2512.09292","title":"Identifying Bias in Machine-generated Text Detection","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2512.10734","title":"Textual Data Bias Detection and Mitigation -- An Extensible Pipeline with Experimental Evaluation","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2602.04687","title":"Investigating Disability Representations in Text-to-Image Models","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2602.11722","title":"PAC-Bayesian Generalization Guarantees for Fairness on Stochastic and Deterministic Classifiers","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2604.19763","title":"Explainable Speech Emotion Recognition: Weighted Attribute Fairness to Model Demographic Contributions to Social Bias","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.26188","title":"Efficient and Interpretable Transformer for Counterfactual Fairness","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2606.05937","title":"Large Language Models are Perplexed by some Political Parties","created":"2026-06-04","cited_by_count":0,"area":null}],"next_cursor":null}