{"total":121,"rows":[{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220,"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":"2106.13219","title":"Towards Understanding and Mitigating Social Biases in Language Models","created":"2021-06-24","cited_by_count":296,"area":null},{"id":"2305.18189","title":"Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models","created":"2023-05-29","cited_by_count":207,"area":null},{"id":"2103.11790","title":"Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do","created":"2021-03-08","cited_by_count":178,"area":null},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168,"area":null},{"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":"2402.09739","title":"QuRating: Selecting High-Quality Data for Training Language Models","created":"2024-02-15","cited_by_count":157,"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":"2201.07520","title":"CM3: A Causal Masked Multimodal Model of the Internet","created":"2022-01-19","cited_by_count":142,"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":"2109.08535","title":"Simple Entity-Centric Questions Challenge Dense Retrievers","created":"2021-09-17","cited_by_count":140,"area":null},{"id":"2212.04612","title":"Training Data Influence Analysis and Estimation: A Survey","created":"2022-12-09","cited_by_count":135,"area":null},{"id":"2108.12084","title":"Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies","created":"2021-08-27","cited_by_count":128,"area":null},{"id":"2101.09523","title":"Debiasing Pre-trained Contextualised Embeddings","created":"2021-01-23","cited_by_count":107,"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":"2112.14168","title":"A Survey on Gender Bias in Natural Language Processing","created":"2021-12-28","cited_by_count":89,"area":null},{"id":"2112.05090","title":"Extending the WILDS Benchmark for Unsupervised Adaptation","created":"2021-12-09","cited_by_count":86,"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":"2104.03514","title":"Low-Complexity Probing via Finding Subnetworks","created":"2021-04-08","cited_by_count":64,"area":null},{"id":"2205.02526","title":"Theories of \"Gender\" in NLP Bias Research","created":"2022-05-05","cited_by_count":62,"area":null},{"id":"2104.07496","title":"Unmasking the Mask -- Evaluating Social Biases in Masked Language Models","created":"2021-04-15","cited_by_count":60,"area":null},{"id":"2205.04610","title":"Towards Intersectionality in Machine Learning: Including More Identities, Handling Underrepresentation, and Performing Evaluation","created":"2022-05-10","cited_by_count":59,"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":"2305.08281","title":"FactKB: Generalizable Factuality Evaluation using Language Models Enhanced with Factual Knowledge","created":"2023-05-14","cited_by_count":55,"area":null},{"id":"2303.13367","title":"ChatGPT and a New Academic Reality: Artificial Intelligence-Written Research Papers and the Ethics of the Large Language Models in Scholarly Publishing","created":"2023-03-21","cited_by_count":52,"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":"2305.12627","title":"MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Prediction","created":"2023-05-22","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":"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":"2101.11974","title":"Disembodied Machine Learning: On the Illusion of Objectivity in NLP","created":"2021-01-28","cited_by_count":37,"area":null},{"id":"2110.05367","title":"Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting","created":"2021-10-11","cited_by_count":35,"area":null},{"id":"2403.20147","title":"IndiBias: A Benchmark Dataset to Measure Social Biases in Language Models for Indian Context","created":"2024-03-29","cited_by_count":32,"area":null},{"id":"2205.11378","title":"Markedness in Visual Semantic AI","created":"2022-05-23","cited_by_count":29,"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":"2210.03070","title":"Toxicity in Multilingual Machine Translation at Scale","created":"2022-10-06","cited_by_count":26,"area":null},{"id":"2109.03300","title":"Hi, my name is Martha: Using names to measure and mitigate bias in generative dialogue models","created":"2021-09-07","cited_by_count":23,"area":null},{"id":"2310.17586","title":"Global Voices, Local Biases: Socio-Cultural Prejudices across Languages","created":"2023-10-26","cited_by_count":23,"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":"2106.10826","title":"Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification","created":"2021-06-21","cited_by_count":20,"area":null},{"id":"2112.07447","title":"Measuring Fairness with Biased Rulers: A Survey on Quantifying Biases in Pretrained Language Models","created":"2021-12-14","cited_by_count":20,"area":null},{"id":"2307.03360","title":"Evaluating Biased Attitude Associations of Language Models in an Intersectional Context","created":"2023-07-07","cited_by_count":20,"area":null},{"id":"2312.02798","title":"Weakly Supervised Detection of Hallucinations in LLM Activations","created":"2023-12-05","cited_by_count":20,"area":null},{"id":"2109.00527","title":"Boosting Search Engines with Interactive Agents","created":"2021-09-01","cited_by_count":19,"area":null},{"id":"2111.06467","title":"SynthBio: A Case Study in Human-AI Collaborative Curation of Text Datasets","created":"2021-11-11","cited_by_count":18,"area":null},{"id":"2204.04026","title":"Fair and Argumentative Language Modeling for Computational Argumentation","created":"2022-04-08","cited_by_count":18,"area":null},{"id":"2210.15144","title":"Gendered Mental Health Stigma in Masked Language Models","created":"2022-10-27","cited_by_count":18,"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":"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":"2207.10245","title":"The Birth of Bias: A case study on the evolution of gender bias in an English language model","created":"2022-07-21","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":"2402.02675","title":"Verifiable evaluations of machine learning models using zkSNARKs","created":"2024-02-05","cited_by_count":16,"area":null},{"id":"2310.14777","title":"Geographical Erasure in Language Generation","created":"2023-10-23","cited_by_count":15,"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":"2311.10395","title":"Bias A-head? Analyzing Bias in Transformer-Based Language Model Attention Heads","created":"2023-11-17","cited_by_count":14,"area":null},{"id":"2106.15355","title":"On the Interaction of Belief Bias and Explanations","created":"2021-06-29","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":"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":"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":"2403.00354","title":"Self-Consistent Reasoning-based Aspect-Sentiment Quad Prediction with Extract-Then-Assign Strategy","created":"2024-03-01","cited_by_count":12,"area":null},{"id":"2407.18454","title":"Fairness Definitions in Language Models Explained","created":"2024-07-26","cited_by_count":11,"area":null},{"id":"2301.12855","title":"How Far Can It Go?: On Intrinsic Gender Bias Mitigation for Text Classification","created":"2023-01-30","cited_by_count":10,"area":null},{"id":"2407.11733","title":"How Are LLMs Mitigating Stereotyping Harms? Learning from Search Engine Studies","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2103.03598","title":"WordBias: An Interactive Visual Tool for Discovering Intersectional Biases Encoded in Word Embeddings","created":"2021-03-05","cited_by_count":8,"area":null},{"id":"2204.10365","title":"Towards an Enhanced Understanding of Bias in Pre-trained Neural Language Models: A Survey with Special Emphasis on Affective Bias","created":"2022-04-21","cited_by_count":8,"area":null},{"id":"2207.04546","title":"FairDistillation: Mitigating Stereotyping in Language Models","created":"2022-07-10","cited_by_count":8,"area":null},{"id":"2204.05356","title":"A Generative Language Model for Few-shot Aspect-Based Sentiment Analysis","created":"2022-04-11","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":"2309.17337","title":"Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Tools","created":"2023-09-29","cited_by_count":7,"area":null},{"id":"2406.00046","title":"Hate Speech Detection with Generalizable Target-aware Fairness","created":"2024-05-28","cited_by_count":7,"area":null},{"id":"2211.08461","title":"Mind Your Bias: A Critical Review of Bias Detection Methods for Contextual Language Models","created":"2022-11-15","cited_by_count":6,"area":null},{"id":"2202.01661","title":"Selection in the Presence of Implicit Bias: The Advantage of Intersectional Constraints","created":"2022-02-03","cited_by_count":5,"area":null},{"id":"2211.11087","title":"Conceptor-Aided Debiasing of Large Language Models","created":"2022-11-20","cited_by_count":5,"area":null},{"id":"2405.06687","title":"Hire Me or Not? Examining Language Model's Behavior with Occupation Attributes","created":"2024-05-06","cited_by_count":5,"area":null},{"id":"2201.06224","title":"Unintended Bias in Language Model-driven Conversational Recommendation","created":"2022-01-17","cited_by_count":4,"area":null},{"id":"2211.13709","title":"Undesirable Biases in NLP: Addressing Challenges of Measurement","created":"2022-11-24","cited_by_count":4,"area":null},{"id":"2305.12376","title":"Measuring Intersectional Biases in Historical Documents","created":"2023-05-21","cited_by_count":4,"area":null},{"id":"2311.12689","title":"Fair Text Classification with Wasserstein Independence","created":"2023-11-21","cited_by_count":4,"area":null},{"id":"2506.03993","title":"Words of Warmth: Trust and Sociability Norms for over 26k English Words","created":"2025-06-04","cited_by_count":4,"area":null},{"id":"2203.04408","title":"iSEA: An Interactive Pipeline for Semantic Error Analysis of NLP Models","created":"2022-03-08","cited_by_count":3,"area":null},{"id":"2208.13899","title":"Debiasing Word Embeddings with Nonlinear Geometry","created":"2022-08-29","cited_by_count":3,"area":null},{"id":"2403.14727","title":"Protected group bias and stereotypes in Large Language Models","created":"2024-03-21","cited_by_count":3,"area":null},{"id":"2411.16527","title":"Profiling Bias in LLMs: Stereotype Dimensions in Contextual Word Embeddings","created":"2024-11-25","cited_by_count":3,"area":null},{"id":"2503.07691","title":"Fair Text Classification via Transferable Representations","created":"2025-03-10","cited_by_count":3,"area":null},{"id":"2503.11962","title":"HInter: Exposing Hidden Intersectional Bias in Large Language Models","created":"2025-03-15","cited_by_count":3,"area":null},{"id":"2507.16557","title":"Exploring Gender Bias in Large Language Models: An In-depth Dive into the German Language","created":"2025-07-22","cited_by_count":3,"area":null},{"id":"2203.05140","title":"Speciesist Language and Nonhuman Animal Bias in English Masked Language Models","created":"2022-03-10","cited_by_count":2,"area":null},{"id":"2301.12139","title":"Bipol: Multi-axes Evaluation of Bias with Explainability in Benchmark Datasets","created":"2023-01-28","cited_by_count":2,"area":null},{"id":"2305.13302","title":"Language-Agnostic Bias Detection in Language Models with Bias Probing","created":"2023-05-22","cited_by_count":2,"area":null},{"id":"2305.19294","title":"Investigating the Effects of Fairness Interventions Using Pointwise Representational Similarity","created":"2023-05-30","cited_by_count":2,"area":null},{"id":"2404.05866","title":"GeniL: A Multilingual Dataset on Generalizing Language","created":"2024-04-08","cited_by_count":2,"area":null},{"id":"2404.16663","title":"Runtime Monitoring and Enforcement of Conditional Fairness in Generative AIs","created":"2024-04-25","cited_by_count":2,"area":null},{"id":"2410.02297","title":"Make Compound Sentences Simple to Analyze: Learning to Split Sentences for Aspect-based Sentiment Analysis","created":"2024-10-03","cited_by_count":2,"area":null},{"id":"2503.09763","title":"BiasConnect: Investigating Bias Interactions in Text-to-Image Models","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2505.17280","title":"Mitigate One, Skew Another? Tackling Intersectional Biases in Text-to-Image Models","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2212.07547","title":"Unsupervised Detection of Contextualized Embedding Bias with Application to Ideology","created":"2022-12-14","cited_by_count":1,"area":null},{"id":"2305.12495","title":"Fair Without Leveling Down: A New Intersectional Fairness Definition","created":"2023-05-21","cited_by_count":1,"area":null},{"id":"2306.07427","title":"Towards Fair and Explainable AI using a Human-Centered AI Approach","created":"2023-06-12","cited_by_count":1,"area":null}],"next_cursor":"100"}