{"total":68,"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":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399,"area":null},{"id":"2302.03169","title":"Data Selection for Language Models via Importance Resampling","created":"2023-02-06","cited_by_count":329,"area":null},{"id":"2203.10020","title":"Challenges and Strategies in Cross-Cultural NLP","created":"2022-03-18","cited_by_count":218,"area":null},{"id":"2106.14574","title":"Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics","created":"2021-06-28","cited_by_count":83,"area":null},{"id":"2411.10915","title":"Bias in Large Language Models: Origin, Evaluation, and Mitigation","created":"2024-11-16","cited_by_count":77,"area":null},{"id":"2102.08886","title":"Towards generalisable hate speech detection: a review on obstacles and solutions","created":"2021-02-17","cited_by_count":66,"area":null},{"id":"2212.08011","title":"Multi-VALUE: A Framework for Cross-Dialectal English NLP","created":"2022-12-15","cited_by_count":53,"area":null},{"id":"2108.02922","title":"Mitigating Dataset Harms Requires Stewardship: Lessons from 1000 Papers","created":"2021-08-06","cited_by_count":49,"area":null},{"id":"2204.03031","title":"VALUE: Understanding Dialect Disparity in NLU","created":"2022-04-06","cited_by_count":47,"area":null},{"id":"2403.00742","title":"Dialect prejudice predicts AI decisions about people's character, employability, and criminality","created":"2024-03-01","cited_by_count":37,"area":null},{"id":"2305.14291","title":"Evaluation of African American Language Bias in Natural Language Generation","created":"2023-05-23","cited_by_count":36,"area":null},{"id":"2402.06853","title":"History, Development, and Principles of Large Language Models-An Introductory Survey","created":"2024-02-10","cited_by_count":30,"area":null},{"id":"2309.17002","title":"Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks","created":"2023-09-29","cited_by_count":27,"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":"2311.08391","title":"A Material Lens on Coloniality in NLP","created":"2023-11-14","cited_by_count":21,"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":"2205.10095","title":"How to keep text private? A systematic review of deep learning methods for privacy-preserving natural language processing","created":"2022-05-20","cited_by_count":16,"area":null},{"id":"2302.12578","title":"Fairness in Language Models Beyond English: Gaps and Challenges","created":"2023-02-24","cited_by_count":16,"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":"2110.13029","title":"Fair Enough: Searching for Sufficient Measures of Fairness","created":"2021-10-25","cited_by_count":14,"area":null},{"id":"2102.11573","title":"Automated Quality Assessment of Cognitive Behavioral Therapy Sessions Through Highly Contextualized Language Representations","created":"2021-02-23","cited_by_count":13,"area":null},{"id":"2207.02253","title":"Putting the Con in Context: Identifying Deceptive Actors in the Game of Mafia","created":"2022-07-05","cited_by_count":13,"area":null},{"id":"2305.13406","title":"DADA: Dialect Adaptation via Dynamic Aggregation of Linguistic Rules","created":"2023-05-22","cited_by_count":13,"area":null},{"id":"2407.09241","title":"The Sociolinguistic Foundations of Language Modeling","created":"2024-07-12","cited_by_count":13,"area":null},{"id":"2110.14839","title":"Hate Speech Classifiers Learn Human-Like Social Stereotypes","created":"2021-10-28","cited_by_count":12,"area":null},{"id":"2109.08792","title":"Learning to be Fair: A Consequentialist Approach to Equitable Decision-Making","created":"2021-09-18","cited_by_count":11,"area":null},{"id":"2410.03448","title":"\"Cold, Calculated, and Condescending\": How AI Identifies and Explains Ableism Compared to Disabled People","created":"2024-10-04","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":"2311.00915","title":"Task-Agnostic Low-Rank Adapters for Unseen English Dialects","created":"2023-11-02","cited_by_count":9,"area":null},{"id":"2207.10032","title":"Detecting Harmful Online Conversational Content towards LGBTQIA+ Individuals","created":"2022-06-15","cited_by_count":8,"area":null},{"id":"2403.06869","title":"Impact of Noisy Supervision in Foundation Model Learning","created":"2024-03-11","cited_by_count":8,"area":null},{"id":"2205.05093","title":"Richer Countries and Richer Representations","created":"2022-05-10","cited_by_count":7,"area":null},{"id":"2208.11321","title":"TESTSGD: Interpretable Testing of Neural Networks Against Subtle Group Discrimination","created":"2022-08-24","cited_by_count":7,"area":null},{"id":"2207.09960","title":"Measuring and signing fairness as performance under multiple stakeholder distributions","created":"2022-07-20","cited_by_count":6,"area":null},{"id":"2404.02323","title":"Toward Informal Language Processing: Knowledge of Slang in Large Language Models","created":"2024-04-02","cited_by_count":6,"area":null},{"id":"2304.12810","title":"Transcending the \"Male Code\": Implicit Masculine Biases in NLP Contexts","created":"2023-04-22","cited_by_count":5,"area":null},{"id":"2306.07500","title":"Adding guardrails to advanced chatbots","created":"2023-06-13","cited_by_count":5,"area":null},{"id":"2504.07100","title":"EnDive: A Cross-Dialect Benchmark for Fairness and Performance in Large Language Models","created":"2025-02-25","cited_by_count":5,"area":null},{"id":"2203.03541","title":"Fairness for Text Classification Tasks with Identity Information Data Augmentation Methods","created":"2022-02-04","cited_by_count":4,"area":null},{"id":"2510.15951","title":"Attention to Non-Adopters","created":"2025-10-10","cited_by_count":4,"area":null},{"id":"2206.08978","title":"Towards a Deep Multi-layered Dialectal Language Analysis: A Case Study of African-American English","created":"2022-06-03","cited_by_count":3,"area":null},{"id":"2309.01413","title":"Hateful Messages: A Conversational Data Set of Hate Speech produced by Adolescents on Discord","created":"2023-09-04","cited_by_count":3,"area":null},{"id":"2503.10789","title":"Data Caricatures: On the Representation of African American Language in Pretraining Corpora","created":"2025-03-13","cited_by_count":3,"area":null},{"id":"2507.07748","title":"When Large Language Models Meet Law: Dual-Lens Taxonomy, Technical Advances, and Ethical Governance","created":"2025-07-10","cited_by_count":3,"area":null},{"id":"2401.11487","title":"Towards Better Inclusivity: A Diverse Tweet Corpus of English Varieties","created":"2024-01-21","cited_by_count":2,"area":null},{"id":"2407.13982","title":"Reexamining Racial Disparities in Automatic Speech Recognition Performance: The Role of Confounding by Provenance","created":"2024-07-19","cited_by_count":2,"area":null},{"id":"2409.13843","title":"STOP! Benchmarking Large Language Models with Sensitivity Testing on Offensive Progressions","created":"2024-09-20","cited_by_count":2,"area":null},{"id":"2505.21816","title":"Revisiting Common Assumptions about Arabic Dialects in NLP","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2601.16349","title":"Regional Bias in Large Language Models","created":"2026-01-22","cited_by_count":2,"area":null},{"id":"2605.06901","title":"Reflections and New Directions for Human-Centered Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2112.13758","title":"Bridging the Gap: Using Deep Acoustic Representations to Learn Grounded Language from Percepts and Raw Speech","created":"2021-12-27","cited_by_count":1,"area":null},{"id":"2401.01262","title":"Fairness Certification for Natural Language Processing and Large Language Models","created":"2024-01-02","cited_by_count":1,"area":null},{"id":"2406.09977","title":"Disentangling Dialect from Social Bias via Multitask Learning to Improve Fairness","created":"2024-06-14","cited_by_count":1,"area":null},{"id":"2409.01539","title":"It is Time to Develop an Auditing Framework to Promote Value Aware Chatbots","created":"2024-09-03","cited_by_count":1,"area":null},{"id":"2410.19812","title":"Ethics Whitepaper: Whitepaper on Ethical Research into Large Language Models","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2210.03352","title":"The Ethical Risks of Analyzing Crisis Events on Social Media with Machine Learning","created":"2022-10-07","cited_by_count":0,"area":null},{"id":"2302.01997","title":"Less, but Stronger: On the Value of Strong Heuristics in Semi-supervised Learning for Software Analytics","created":"2023-02-03","cited_by_count":0,"area":null},{"id":"2304.11485","title":"Understanding Lexical Biases when Identifying Gang-related Social Media Communications","created":"2023-04-22","cited_by_count":0,"area":null},{"id":"2307.13616","title":"AI and ethics in insurance: a new solution to mitigate proxy discrimination in risk modeling","created":"2023-07-25","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":"2408.00612","title":"Downstream bias mitigation is all you need","created":"2024-08-01","cited_by_count":0,"area":null},{"id":"2502.07058","title":"Using Contextually Aligned Online Reviews to Measure LLMs' Performance Disparities Across Language Varieties","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2507.03142","title":"From Measurement to Mitigation: Exploring the Transferability of Debiasing Approaches to Gender Bias in Maltese Language Models","created":"2025-07-03","cited_by_count":0,"area":null},{"id":"2601.13346","title":"AfroScope: A Framework for Studying the Linguistic Landscape of Africa","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2602.21485","title":"Evaluating the Usage of African-American Vernacular English in Large Language Models","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2607.06544","title":"Rethinking Indic AI from a Lens of Cultural Heritage Preservation","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2608.09280","title":"Is the ACL Responsible NLP Checklist a Box-Ticking Exercise? A Large-Scale Analysis of EMNLP 2025","created":"2026-08-10","cited_by_count":0,"area":null}],"next_cursor":null}