{"total":137,"rows":[{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830,"area":null},{"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":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567,"area":null},{"id":"2208.03274","title":"A Holistic Approach to Undesired Content Detection in the Real World","created":"2022-08-05","cited_by_count":356,"area":null},{"id":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349,"area":null},{"id":"2101.00288","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","created":"2021-01-01","cited_by_count":222,"area":null},{"id":"2303.04381","title":"Automatically Auditing Large Language Models via Discrete Optimization","created":"2023-03-08","cited_by_count":191,"area":null},{"id":"2109.00725","title":"Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond","created":"2021-09-02","cited_by_count":178,"area":null},{"id":"2112.07566","title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","created":"2021-12-14","cited_by_count":135,"area":null},{"id":"2101.09995","title":"Re-imagining Algorithmic Fairness in India and Beyond","created":"2021-01-25","cited_by_count":104,"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":"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":"2106.00545","title":"Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Tests","created":"2021-05-31","cited_by_count":77,"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":"2206.09917","title":"Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models","created":"2022-06-20","cited_by_count":51,"area":null},{"id":"2205.05256","title":"Evaluation Gaps in Machine Learning Practice","created":"2022-05-11","cited_by_count":49,"area":null},{"id":"2208.08831","title":"Discovering Bugs in Vision Models using Off-the-shelf Image Generation and Captioning","created":"2022-08-18","cited_by_count":45,"area":null},{"id":"2403.12025","title":"A Toolbox for Surfacing Health Equity Harms and Biases in Large Language Models","created":"2024-03-18","cited_by_count":45,"area":null},{"id":"2310.00603","title":"Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals","created":"2023-10-01","cited_by_count":44,"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":"2306.08158","title":"Sociodemographic Bias in Language Models: A Survey and Forward Path","created":"2023-06-13","cited_by_count":28,"area":null},{"id":"2210.03535","title":"From plane crashes to algorithmic harm: applicability of safety engineering frameworks for responsible ML","created":"2022-10-06","cited_by_count":27,"area":null},{"id":"2106.01070","title":"Testing Group Fairness via Optimal Transport Projections","created":"2021-06-02","cited_by_count":23,"area":null},{"id":"2304.01391","title":"Counterfactual Learning on Graphs: A Survey","created":"2023-04-03","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":"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":"2202.02943","title":"Learning fair representation with a parametric integral probability metric","created":"2022-02-07","cited_by_count":20,"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":"2205.03302","title":"Necessity and Sufficiency for Explaining Text Classifiers: A Case Study in Hate Speech Detection","created":"2022-05-06","cited_by_count":18,"area":null},{"id":"2309.08573","title":"Indian-BhED: A Dataset for Measuring India-Centric Biases in Large Language Models","created":"2023-09-15","cited_by_count":18,"area":null},{"id":"2107.08362","title":"Probabilistic Verification of Neural Networks Against Group Fairness","created":"2021-07-18","cited_by_count":17,"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":"2106.05894","title":"Synthesizing Adversarial Negative Responses for Robust Response Ranking and Evaluation","created":"2021-06-10","cited_by_count":16,"area":null},{"id":"2205.08704","title":"Accurate Fairness: Improving Individual Fairness without Trading Accuracy","created":"2022-05-18","cited_by_count":16,"area":null},{"id":"2306.06135","title":"Safety and Fairness for Content Moderation in Generative Models","created":"2023-06-09","cited_by_count":16,"area":null},{"id":"2106.04484","title":"Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions","created":"2021-06-08","cited_by_count":15,"area":null},{"id":"2107.08176","title":"Automatic Fairness Testing of Neural Classifiers through Adversarial Sampling","created":"2021-07-17","cited_by_count":14,"area":null},{"id":"2310.12803","title":"Data Augmentations for Improved (Large) Language Model Generalization","created":"2023-10-19","cited_by_count":14,"area":null},{"id":"2205.00504","title":"Domain Adaptation meets Individual Fairness. And they get along","created":"2022-05-01","cited_by_count":13,"area":null},{"id":"2206.13757","title":"Flexible text generation for counterfactual fairness probing","created":"2022-06-28","cited_by_count":13,"area":null},{"id":"2103.16785","title":"Individually Fair Gradient Boosting","created":"2021-03-31","cited_by_count":12,"area":null},{"id":"2302.03465","title":"Robustness Implies Fairness in Causal Algorithmic Recourse","created":"2023-02-07","cited_by_count":12,"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":"2211.03374","title":"Deep Causal Learning: Representation, Discovery and Inference","created":"2022-11-07","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":"2310.15398","title":"\"One-Size-Fits-All\"? Examining Expectations around What Constitute \"Fair\" or \"Good\" NLG System Behaviors","created":"2023-10-23","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":"2103.06828","title":"Wasserstein Robust Classification with Fairness Constraints","created":"2021-03-11","cited_by_count":10,"area":null},{"id":"2108.01721","title":"Improving Counterfactual Generation for Fair Hate Speech Detection","created":"2021-08-03","cited_by_count":10,"area":null},{"id":"2201.01811","title":"CausalSim: A Causal Framework for Unbiased Trace-Driven Simulation","created":"2022-01-05","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":"2109.04053","title":"Table-based Fact Verification with Salience-aware Learning","created":"2021-09-09","cited_by_count":9,"area":null},{"id":"2311.05420","title":"Counterfactually Fair Representation","created":"2023-11-09","cited_by_count":9,"area":null},{"id":"2110.11205","title":"Robustness through Data Augmentation Loss Consistency","created":"2021-10-21","cited_by_count":8,"area":null},{"id":"2210.05457","title":"Are Pretrained Multilingual Models Equally Fair Across Languages?","created":"2022-10-11","cited_by_count":8,"area":null},{"id":"2305.11673","title":"Bias Beyond English: Counterfactual Tests for Bias in Sentiment Analysis in Four Languages","created":"2023-05-19","cited_by_count":8,"area":null},{"id":"2405.19433","title":"Beyond Agreement: Diagnosing the Rationale Alignment of Automated Essay Scoring Methods based on Linguistically-informed Counterfactuals","created":"2024-05-29","cited_by_count":8,"area":null},{"id":"2409.01977","title":"Counterfactual Fairness by Combining Factual and Counterfactual Predictions","created":"2024-09-03","cited_by_count":8,"area":null},{"id":"2506.07947","title":"Statistical Hypothesis Testing for Auditing Robustness in Language Models","created":"2025-06-09","cited_by_count":8,"area":null},{"id":"2103.11023","title":"Individually Fair Ranking","created":"2021-03-19","cited_by_count":7,"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":"2210.03167","title":"FAST: Improving Controllability for Text Generation with Feedback Aware Self-Training","created":"2022-10-06","cited_by_count":7,"area":null},{"id":"2303.00673","title":"Fairness Evaluation in Text Classification: Machine Learning Practitioner Perspectives of Individual and Group Fairness","created":"2023-03-01","cited_by_count":7,"area":null},{"id":"2306.00025","title":"Disentangling and Operationalizing AI Fairness at LinkedIn","created":"2023-05-30","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":"2104.04144","title":"Individual Explanations in Machine Learning Models: A Survey for Practitioners","created":"2021-04-09","cited_by_count":6,"area":null},{"id":"2111.08856","title":"Fairness Testing of Deep Image Classification with Adequacy Metrics","created":"2021-11-17","cited_by_count":6,"area":null},{"id":"2205.15049","title":"Metrizing Fairness","created":"2022-05-30","cited_by_count":6,"area":null},{"id":"2210.15500","title":"COFFEE: Counterfactual Fairness for Personalized Text Generation in Explainable Recommendation","created":"2022-10-14","cited_by_count":6,"area":null},{"id":"2304.08275","title":"Implementing Responsible AI: Tensions and Trade-Offs Between Ethics Aspects","created":"2023-04-17","cited_by_count":6,"area":null},{"id":"2403.07310","title":"How does promoting the minority fraction affect generalization? A theoretical study of the one-hidden-layer neural network on group imbalance","created":"2024-03-12","cited_by_count":6,"area":null},{"id":"2203.08670","title":"Measuring Fairness of Text Classifiers via Prediction Sensitivity","created":"2022-03-16","cited_by_count":5,"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":"2208.06987","title":"The Causal Structure of Domain Invariant Supervised Representation Learning","created":"2022-08-15","cited_by_count":5,"area":null},{"id":"2209.09975","title":"Power of Explanations: Towards automatic debiasing in hate speech detection","created":"2022-09-07","cited_by_count":5,"area":null},{"id":"2212.10154","title":"Human-Guided Fair Classification for Natural Language Processing","created":"2022-12-20","cited_by_count":5,"area":null},{"id":"2302.05674","title":"Counter-GAP: Counterfactual Bias Evaluation through Gendered Ambiguous Pronouns","created":"2023-02-11","cited_by_count":5,"area":null},{"id":"2303.02874","title":"Adversarial Sampling for Fairness Testing in Deep Neural Network","created":"2023-03-06","cited_by_count":5,"area":null},{"id":"2306.07152","title":"Measuring Sentiment Bias in Machine Translation","created":"2023-06-12","cited_by_count":5,"area":null},{"id":"2308.07779","title":"Do We Fully Understand Students' Knowledge States? Identifying and Mitigating Answer Bias in Knowledge Tracing","created":"2023-08-15","cited_by_count":5,"area":null},{"id":"2404.01921","title":"A Rationale-centric Counterfactual Data Augmentation Method for Cross-Document Event Coreference Resolution","created":"2024-04-02","cited_by_count":5,"area":null},{"id":"2602.04398","title":"Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying Prompts","created":"2026-02-04","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":"2310.17687","title":"Consistent End-to-End Estimation for Counterfactual Fairness","created":"2023-10-26","cited_by_count":4,"area":null},{"id":"2312.05551","title":"Multi-dimensional Fair Federated Learning","created":"2023-12-09","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":"2202.03792","title":"Counterfactual Multi-Token Fairness in Text Classification","created":"2022-02-08","cited_by_count":3,"area":null},{"id":"2210.06759","title":"Outlier-Robust Group Inference via Gradient Space Clustering","created":"2022-10-13","cited_by_count":3,"area":null},{"id":"2402.00711","title":"Explaining Text Classifiers with Counterfactual Representations","created":"2024-02-01","cited_by_count":3,"area":null},{"id":"2404.06619","title":"FairPair: A Robust Evaluation of Biases in Language Models through Paired Perturbations","created":"2024-04-09","cited_by_count":3,"area":null},{"id":"2406.14154","title":"Watching the Watchers: A Comparative Fairness Audit of Cloud-based Content Moderation Services","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2406.17104","title":"Automated Adversarial Discovery for Safety Classifiers","created":"2024-06-24","cited_by_count":3,"area":null},{"id":"2407.11203","title":"The Life Cycle of Large Language Models: A Review of Biases in Education","created":"2024-06-03","cited_by_count":3,"area":null},{"id":"2504.11504","title":"Counterfactual Fairness Evaluation of Machine Learning Models on Educational Datasets","created":"2025-04-15","cited_by_count":3,"area":null},{"id":"2508.07111","title":"Investigating Intersectional Bias in Large Language Models using Confidence Disparities in Coreference Resolution","created":"2025-08-09","cited_by_count":3,"area":null},{"id":"2508.15374","title":"Minority Collective Action for User-Side Fairness","created":"2025-08-21","cited_by_count":3,"area":null},{"id":"2106.08914","title":"$C^3$: Compositional Counterfactual Contrastive Learning for Video-grounded Dialogues","created":"2021-06-16","cited_by_count":2,"area":null},{"id":"2202.04504","title":"Prediction Sensitivity: Continual Audit of Counterfactual Fairness in Deployed Classifiers","created":"2022-02-09","cited_by_count":2,"area":null}],"next_cursor":"100"}