{"total":254,"rows":[{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220,"area":null},{"id":"2406.17557","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","created":"2024-06-25","cited_by_count":1160,"area":null},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966,"area":null},{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799,"area":null},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744,"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":"2304.05335","title":"Toxicity in ChatGPT: Analyzing Persona-assigned Language Models","created":"2023-04-11","cited_by_count":360,"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":"2305.08283","title":"From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models","created":"2023-05-15","cited_by_count":260,"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":"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":"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":"2101.09523","title":"Debiasing Pre-trained Contextualised Embeddings","created":"2021-01-23","cited_by_count":107,"area":null},{"id":"2104.05893","title":"NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media","created":"2021-04-13","cited_by_count":107,"area":null},{"id":"2109.03646","title":"Sustainable Modular Debiasing of Language Models","created":"2021-09-08","cited_by_count":100,"area":null},{"id":"2110.08527","title":"An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models","created":"2021-10-16","cited_by_count":97,"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":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"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":"2109.05704","title":"Mitigating Language-Dependent Ethnic Bias in BERT","created":"2021-09-13","cited_by_count":87,"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":"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":"2203.13928","title":"On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations","created":"2022-03-25","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":"2110.13796","title":"Post-processing for Individual Fairness","created":"2021-10-26","cited_by_count":61,"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":"2205.00551","title":"Gender Bias in Masked Language Models for Multiple Languages","created":"2022-05-01","cited_by_count":60,"area":null},{"id":"2409.11360","title":"AI Suggestions Homogenize Writing Toward Western Styles and Diminish Cultural Nuances","created":"2024-09-17","cited_by_count":60,"area":null},{"id":"2312.15524","title":"The Challenge of Using LLMs to Simulate Human Behavior: A Causal Inference Perspective","created":"2023-12-24","cited_by_count":59,"area":null},{"id":"2306.11507","title":"TrustGPT: A Benchmark for Trustworthy and Responsible Large Language Models","created":"2023-06-20","cited_by_count":58,"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":"2106.02124","title":"How to Adapt Your Pretrained Multilingual Model to 1600 Languages","created":"2021-06-03","cited_by_count":54,"area":null},{"id":"2104.08666","title":"Worst of Both Worlds: Biases Compound in Pre-trained Vision-and-Language Models","created":"2021-04-18","cited_by_count":52,"area":null},{"id":"2312.01261","title":"TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Models","created":"2023-12-03","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":"2302.02463","title":"Nationality Bias in Text Generation","created":"2023-02-05","cited_by_count":50,"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":"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":"2202.11923","title":"Welcome to the Modern World of Pronouns: Identity-Inclusive Natural Language Processing beyond Gender","created":"2022-02-24","cited_by_count":47,"area":null},{"id":"2102.05281","title":"Biomedical Question Answering: A Survey of Approaches and Challenges","created":"2021-02-10","cited_by_count":46,"area":null},{"id":"2306.03950","title":"MISGENDERED: Limits of Large Language Models in Understanding Pronouns","created":"2023-06-06","cited_by_count":43,"area":null},{"id":"2309.01291","title":"Generative Social Choice","created":"2023-09-03","cited_by_count":43,"area":null},{"id":"2306.11932","title":"Opportunities and Risks of LLMs for Scalable Deliberation with Polis","created":"2023-06-20","cited_by_count":42,"area":null},{"id":"2402.12649","title":"Bias in Language Models: Beyond Trick Tests and Toward RUTEd Evaluation","created":"2024-02-20","cited_by_count":41,"area":null},{"id":"2110.00672","title":"Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Models","created":"2021-10-01","cited_by_count":39,"area":null},{"id":"2210.04337","title":"Quantifying Social Biases Using Templates is Unreliable","created":"2022-10-09","cited_by_count":39,"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":"2206.11684","title":"Theory-Grounded Measurement of U.S. Social Stereotypes in English Language Models","created":"2022-06-23","cited_by_count":35,"area":null},{"id":"2403.00277","title":"Gender Bias in Large Language Models across Multiple Languages","created":"2024-03-01","cited_by_count":35,"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":"2211.15458","title":"Validating Large Language Models with ReLM","created":"2022-11-21","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":"2407.12824","title":"Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models","created":"2024-07-02","cited_by_count":32,"area":null},{"id":"2104.06999","title":"Detecting Cross-Geographic Biases in Toxicity Modeling on Social Media","created":"2021-04-14","cited_by_count":31,"area":null},{"id":"2210.14975","title":"MABEL: Attenuating Gender Bias using Textual Entailment Data","created":"2022-10-26","cited_by_count":31,"area":null},{"id":"2307.01503","title":"On Evaluating and Mitigating Gender Biases in Multilingual Settings","created":"2023-07-04","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":"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":"2306.04597","title":"Language Models Get a Gender Makeover: Mitigating Gender Bias with Few-Shot Data Interventions","created":"2023-06-07","cited_by_count":28,"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":"2208.00636","title":"Interacting with next-phrase suggestions: How suggestion systems aid and influence the cognitive processes of writing","created":"2022-08-01","cited_by_count":27,"area":null},{"id":"2402.02056","title":"AnthroScore: A Computational Linguistic Measure of Anthropomorphism","created":"2024-02-03","cited_by_count":27,"area":null},{"id":"2210.03070","title":"Toxicity in Multilingual Machine Translation at Scale","created":"2022-10-06","cited_by_count":26,"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":"2305.13198","title":"Multilingual Holistic Bias: Extending Descriptors and Patterns to Unveil Demographic Biases in Languages at Scale","created":"2023-05-22","cited_by_count":24,"area":null},{"id":"2305.14711","title":"Gender Biases in Automatic Evaluation Metrics for Image Captioning","created":"2023-05-24","cited_by_count":24,"area":null},{"id":"2106.02596","title":"Understanding and Countering Stereotypes: A Computational Approach to the Stereotype Content Model","created":"2021-06-04","cited_by_count":23,"area":null},{"id":"2106.03921","title":"Measuring and Improving BERT's Mathematical Abilities by Predicting the Order of Reasoning","created":"2021-06-07","cited_by_count":23,"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":"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":"2103.11263","title":"Self-Supervised Test-Time Learning for Reading Comprehension","created":"2021-03-20","cited_by_count":22,"area":null},{"id":"2211.05617","title":"Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Survey","created":"2022-11-10","cited_by_count":22,"area":null},{"id":"2312.15398","title":"Fairness-Aware Structured Pruning in Transformers","created":"2023-12-24","cited_by_count":22,"area":null},{"id":"2205.11374","title":"Looking for a Handsome Carpenter! Debiasing GPT-3 Job Advertisements","created":"2022-05-23","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":"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":"2304.08637","title":"An Evaluation on Large Language Model Outputs: Discourse and Memorization","created":"2023-04-17","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":"2307.03360","title":"Evaluating Biased Attitude Associations of Language Models in an Intersectional Context","created":"2023-07-07","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":"2312.02798","title":"Weakly Supervised Detection of Hallucinations in LLM Activations","created":"2023-12-05","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":"2110.15766","title":"NxMTransformer: Semi-Structured Sparsification for Natural Language Understanding via ADMM","created":"2021-10-28","cited_by_count":19,"area":null},{"id":"2309.11568","title":"BTLM-3B-8K: 7B Parameter Performance in a 3B Parameter Model","created":"2023-09-20","cited_by_count":19,"area":null},{"id":"2312.05662","title":"Understanding the Effect of Model Compression on Social Bias in Large Language Models","created":"2023-12-09","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":"2203.07523","title":"Sense Embeddings are also Biased--Evaluating Social Biases in Static and Contextualised Sense Embeddings","created":"2022-03-14","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":"2401.06947","title":"Parameter-Efficient Detoxification with Contrastive Decoding","created":"2024-01-13","cited_by_count":18,"area":null},{"id":"2312.01700","title":"Data Management For Training Large Language Models: A Survey","created":"2023-12-04","cited_by_count":17,"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":"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}],"next_cursor":"100"}