{"total":234,"rows":[{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202,"area":null},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639,"area":null},{"id":"2101.11718","title":"BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation","created":"2021-01-27","cited_by_count":412,"area":null},{"id":"2304.09848","title":"Evaluating Verifiability in Generative Search Engines","created":"2023-04-19","cited_by_count":303,"area":null},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2104.02145","title":"What Will it Take to Fix Benchmarking in Natural Language Understanding?","created":"2021-04-05","cited_by_count":203,"area":null},{"id":"2105.04054","title":"Societal Biases in Language Generation: Progress and Challenges","created":"2021-05-10","cited_by_count":202,"area":null},{"id":"2308.14921","title":"Gender bias and stereotypes in Large Language Models","created":"2023-08-28","cited_by_count":187,"area":null},{"id":"2102.04130","title":"Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models","created":"2021-02-08","cited_by_count":141,"area":null},{"id":"2106.08503","title":"Understanding and Evaluating Racial Biases in Image Captioning","created":"2021-06-16","cited_by_count":108,"area":null},{"id":"2104.06390","title":"Detoxifying Language Models Risks Marginalizing Minority Voices","created":"2021-04-13","cited_by_count":107,"area":null},{"id":"2202.07304","title":"XAI for Transformers: Better Explanations through Conservative Propagation","created":"2022-02-15","cited_by_count":100,"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":"2107.06641","title":"Trustworthy AI: A Computational Perspective","created":"2021-07-12","cited_by_count":93,"area":null},{"id":"2112.14168","title":"A Survey on Gender Bias in Natural Language Processing","created":"2021-12-28","cited_by_count":89,"area":null},{"id":"2404.00929","title":"A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias","created":"2024-04-01","cited_by_count":84,"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":"2108.03362","title":"On Measures of Biases and Harms in NLP","created":"2021-08-07","cited_by_count":81,"area":null},{"id":"2105.02732","title":"What's in the Box? A Preliminary Analysis of Undesirable Content in the Common Crawl Corpus","created":"2021-05-06","cited_by_count":80,"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":"2103.06413","title":"FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders","created":"2021-03-11","cited_by_count":75,"area":null},{"id":"2106.11410","title":"A Survey of Race, Racism, and Anti-Racism in NLP","created":"2021-06-21","cited_by_count":75,"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":"2109.03858","title":"Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation","created":"2021-09-08","cited_by_count":62,"area":null},{"id":"2205.02526","title":"Theories of \"Gender\" in NLP Bias Research","created":"2022-05-05","cited_by_count":62,"area":null},{"id":"2404.01349","title":"Fairness in Large Language Models: A Taxonomic Survey","created":"2024-03-31","cited_by_count":58,"area":null},{"id":"2101.09688","title":"Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Models","created":"2021-01-24","cited_by_count":57,"area":null},{"id":"2209.12226","title":"Re-contextualizing Fairness in NLP: The Case of India","created":"2022-09-25","cited_by_count":55,"area":null},{"id":"2306.05550","title":"Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Tasks","created":"2023-06-08","cited_by_count":51,"area":null},{"id":"2101.10001","title":"Diverse Adversaries for Mitigating Bias in Training","created":"2021-01-25","cited_by_count":48,"area":null},{"id":"2210.02938","title":"Debiasing isn't enough! -- On the Effectiveness of Debiasing MLMs and their Social Biases in Downstream Tasks","created":"2022-10-06","cited_by_count":48,"area":null},{"id":"2204.03031","title":"VALUE: Understanding Dialect Disparity in NLU","created":"2022-04-06","cited_by_count":47,"area":null},{"id":"2110.14189","title":"Robust Contrastive Learning Using Negative Samples with Diminished Semantics","created":"2021-10-27","cited_by_count":43,"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":"2311.14693","title":"Benefits and Harms of Large Language Models in Digital Mental Health","created":"2023-11-07","cited_by_count":40,"area":null},{"id":"2210.04337","title":"Quantifying Social Biases Using Templates is Unreliable","created":"2022-10-09","cited_by_count":39,"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":"2206.09860","title":"Fewer Errors, but More Stereotypes? The Effect of Model Size on Gender Bias","created":"2022-06-20","cited_by_count":33,"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":"2205.12771","title":"Does Moral Code Have a Moral Code? Probing Delphi's Moral Philosophy","created":"2022-05-25","cited_by_count":31,"area":null},{"id":"2110.00521","title":"Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lens","created":"2021-10-01","cited_by_count":30,"area":null},{"id":"2210.11471","title":"Choose Your Lenses: Flaws in Gender Bias Evaluation","created":"2022-10-20","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":"2110.03212","title":"Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates","created":"2021-10-07","cited_by_count":27,"area":null},{"id":"2309.14381","title":"Survey of Social Bias in Vision-Language Models","created":"2023-09-24","cited_by_count":26,"area":"mllm"},{"id":"2305.04990","title":"Explanation-based Finetuning Makes Models More Robust to Spurious Cues","created":"2023-05-08","cited_by_count":25,"area":null},{"id":"2307.10514","title":"Building Socio-culturally Inclusive Stereotype Resources with Community Engagement","created":"2023-07-20","cited_by_count":25,"area":null},{"id":"2112.04899","title":"Assessing Fairness in the Presence of Missing Data","created":"2021-12-07","cited_by_count":24,"area":null},{"id":"2205.11601","title":"Challenges in Measuring Bias via Open-Ended Language Generation","created":"2022-05-23","cited_by_count":24,"area":null},{"id":"2206.04394","title":"Xplique: A Deep Learning Explainability Toolbox","created":"2022-06-09","cited_by_count":24,"area":null},{"id":"2301.09211","title":"An Empirical Study of Metrics to Measure Representational Harms in Pre-Trained Language Models","created":"2023-01-22","cited_by_count":24,"area":null},{"id":"2306.16244","title":"CBBQ: A Chinese Bias Benchmark Dataset Curated with Human-AI Collaboration for Large Language Models","created":"2023-06-28","cited_by_count":23,"area":null},{"id":"2109.08256","title":"Ethics Sheet for Automatic Emotion Recognition and Sentiment Analysis","created":"2021-09-17","cited_by_count":22,"area":null},{"id":"2211.11109","title":"Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairness","created":"2022-11-20","cited_by_count":21,"area":null},{"id":"2306.15298","title":"Gender Bias in BERT -- Measuring and Analysing Biases through Sentiment Rating in a Realistic Downstream Classification Task","created":"2023-06-27","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":"2305.15020","title":"An Efficient Multilingual Language Model Compression through Vocabulary Trimming","created":"2023-05-24","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":"2502.01926","title":"Fairness through Difference Awareness: Measuring Desired Group Discrimination in LLMs","created":"2025-02-04","cited_by_count":20,"area":null},{"id":"2106.08680","title":"Evaluating Gender Bias in Hindi-English Machine Translation","created":"2021-06-16","cited_by_count":19,"area":null},{"id":"2107.01183","title":"Ethics Sheets for AI Tasks","created":"2021-07-02","cited_by_count":18,"area":null},{"id":"2210.07455","title":"Controlling Bias Exposure for Fair Interpretable Predictions","created":"2022-10-14","cited_by_count":18,"area":null},{"id":"2307.03195","title":"A Comprehensive Survey of Artificial Intelligence Techniques for Talent Analytics","created":"2023-07-03","cited_by_count":18,"area":null},{"id":"2111.03015","title":"Modeling Techniques for Machine Learning Fairness: A Survey","created":"2021-11-04","cited_by_count":17,"area":null},{"id":"2108.02854","title":"GENder-IT: An Annotated English-Italian Parallel Challenge Set for Cross-Linguistic Natural Gender Phenomena","created":"2021-08-05","cited_by_count":16,"area":null},{"id":"2109.10052","title":"Stepmothers are mean and academics are pretentious: What do pretrained language models learn about you?","created":"2021-09-21","cited_by_count":16,"area":null},{"id":"2308.04346","title":"Unmasking Nationality Bias: A Study of Human Perception of Nationalities in AI-Generated Articles","created":"2023-08-08","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":"2311.03311","title":"Unraveling Downstream Gender Bias from Large Language Models: A Study on AI Educational Writing Assistance","created":"2023-11-06","cited_by_count":15,"area":null},{"id":"2408.06518","title":"Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Models","created":"2024-08-12","cited_by_count":15,"area":null},{"id":"2410.09992","title":"Evaluating Gender Bias of LLMs in Making Morality Judgements","created":"2024-10-13","cited_by_count":15,"area":null},{"id":"2109.08613","title":"Adversarial Scrubbing of Demographic Information for Text Classification","created":"2021-09-17","cited_by_count":14,"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":"2105.06604","title":"Towards Equity and Algorithmic Fairness in Student Grade Prediction","created":"2021-05-14","cited_by_count":13,"area":null},{"id":"2111.13259","title":"Identification of Bias Against People with Disabilities in Sentiment Analysis and Toxicity Detection Models","created":"2021-11-25","cited_by_count":13,"area":null},{"id":"2204.03558","title":"Mapping the Multilingual Margins: Intersectional Biases of Sentiment Analysis Systems in English, Spanish, and Arabic","created":"2022-04-07","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":"2311.04479","title":"Twitter Sentiment Analysis of Covid Vacciness","created":"2023-11-08","cited_by_count":13,"area":null},{"id":"2405.06996","title":"Quite Good, but Not Enough: Nationality Bias in Large Language Models -- A Case Study of ChatGPT","created":"2024-05-11","cited_by_count":13,"area":null},{"id":"2405.15185","title":"An Evaluation of Estimative Uncertainty in Large Language Models","created":"2024-05-24","cited_by_count":13,"area":null},{"id":"2506.11880","title":"Addressing Bias in LLMs: Strategies and Application to Fair AI-based Recruitment","created":"2025-06-13","cited_by_count":13,"area":null},{"id":"2204.06827","title":"How Gender Debiasing Affects Internal Model Representations, and Why It Matters","created":"2022-04-14","cited_by_count":12,"area":null},{"id":"2305.17013","title":"D-CALM: A Dynamic Clustering-based Active Learning Approach for Mitigating Bias","created":"2023-05-26","cited_by_count":12,"area":null},{"id":"2310.12318","title":"The Sentiment Problem: A Critical Survey towards Deconstructing Sentiment Analysis","created":"2023-10-18","cited_by_count":12,"area":null},{"id":"2109.04738","title":"On the validity of pre-trained transformers for natural language processing in the software engineering domain","created":"2021-09-10","cited_by_count":11,"area":null},{"id":"2110.00911","title":"Enhancing Model Robustness and Fairness with Causality: A Regularization Approach","created":"2021-10-03","cited_by_count":11,"area":null},{"id":"2305.13088","title":"Should We Attend More or Less? Modulating Attention for Fairness","created":"2023-05-22","cited_by_count":11,"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":"2404.16123","title":"FairDeDup: Detecting and Mitigating Vision-Language Fairness Disparities in Semantic Dataset Deduplication","created":"2024-04-24","cited_by_count":11,"area":"mllm"},{"id":"2412.15993","title":"Fearful Falcons and Angry Llamas: Emotion Category Annotations of Arguments by Humans and LLMs","created":"2024-12-20","cited_by_count":11,"area":null},{"id":"2205.11605","title":"On Measuring Social Biases in Prompt-Based Multi-Task Learning","created":"2022-05-23","cited_by_count":10,"area":null},{"id":"2405.00588","title":"Are Models Biased on Text without Gender-related Language?","created":"2024-05-01","cited_by_count":10,"area":null},{"id":"2410.16498","title":"Natural Language Processing for Human Resources: A Survey","created":"2024-10-21","cited_by_count":10,"area":null},{"id":"2104.05232","title":"Double Perturbation: On the Robustness of Robustness and Counterfactual Bias Evaluation","created":"2021-04-12","cited_by_count":9,"area":null},{"id":"2106.09462","title":"pysentimiento: A Python Toolkit for Opinion Mining and Social NLP tasks","created":"2021-06-17","cited_by_count":9,"area":null},{"id":"2205.06135","title":"Fair NLP Models with Differentially Private Text Encoders","created":"2022-05-12","cited_by_count":9,"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":"2310.18877","title":"Pre-trained Speech Processing Models Contain Human-Like Biases that Propagate to Speech Emotion Recognition","created":"2023-10-29","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}],"next_cursor":"100"}