{"total":74,"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":"2110.05719","title":"Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations","created":"2021-10-12","cited_by_count":314,"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":"2202.07304","title":"XAI for Transformers: Better Explanations through Conservative Propagation","created":"2022-02-15","cited_by_count":100,"area":null},{"id":"2108.12237","title":"Evaluating the Robustness of Neural Language Models to Input Perturbations","created":"2021-08-27","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":"2108.03362","title":"On Measures of Biases and Harms in NLP","created":"2021-08-07","cited_by_count":81,"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":"2205.12586","title":"Perturbation Augmentation for Fairer NLP","created":"2022-05-25","cited_by_count":52,"area":null},{"id":"2302.02463","title":"Nationality Bias in Text Generation","created":"2023-02-05","cited_by_count":50,"area":null},{"id":"2205.05256","title":"Evaluation Gaps in Machine Learning Practice","created":"2022-05-11","cited_by_count":49,"area":null},{"id":"2212.10020","title":"On the Blind Spots of Model-Based Evaluation Metrics for Text Generation","created":"2022-12-20","cited_by_count":49,"area":null},{"id":"2210.04337","title":"Quantifying Social Biases Using Templates is Unreliable","created":"2022-10-09","cited_by_count":39,"area":null},{"id":"2305.11242","title":"Comparing Biases and the Impact of Multilingual Training across Multiple Languages","created":"2023-05-18","cited_by_count":36,"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":"2106.06830","title":"Evaluating Entity Disambiguation and the Role of Popularity in Retrieval-Based NLP","created":"2021-06-12","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":"2106.05532","title":"How Robust are Model Rankings: A Leaderboard Customization Approach for Equitable Evaluation","created":"2021-06-10","cited_by_count":24,"area":null},{"id":"2603.13285","title":"Brittlebench: Quantifying LLM robustness via prompt sensitivity","created":"2026-02-27","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":"2210.02667","title":"A Human Rights-Based Approach to Responsible AI","created":"2022-10-06","cited_by_count":20,"area":null},{"id":"2212.10526","title":"Open Domain Multi-document Summarization: A Comprehensive Study of Model Brittleness under Retrieval","created":"2022-12-20","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":"2109.10444","title":"Fairness-aware Class Imbalanced Learning","created":"2021-09-21","cited_by_count":19,"area":null},{"id":"2110.07159","title":"Interpreting the Robustness of Neural NLP Models to Textual Perturbations","created":"2021-10-14","cited_by_count":17,"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":"2104.07505","title":"Quantifying Gender Bias Towards Politicians in Cross-Lingual Language Models","created":"2021-04-15","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":"2105.03048","title":"Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates","created":"2021-05-07","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":"2503.01623","title":"Lost in Moderation: How Commercial Content Moderation APIs Over- and Under-Moderate Group-Targeted Hate Speech and Linguistic Variations","created":"2025-03-03","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":"2302.03788","title":"Toward a Theory of Causation for Interpreting Neural Code Models","created":"2023-02-07","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":"2305.07378","title":"Surfacing Biases in Large Language Models using Contrastive Input Decoding","created":"2023-05-12","cited_by_count":11,"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":"2102.03671","title":"From Toxicity in Online Comments to Incivility in American News: Proceed with Caution","created":"2021-02-06","cited_by_count":8,"area":null},{"id":"2306.01117","title":"Examining the Causal Effect of First Names on Language Models: The Case of Social Commonsense Reasoning","created":"2023-06-01","cited_by_count":8,"area":"lr"},{"id":"2401.09972","title":"Better Explain Transformers by Illuminating Important Information","created":"2024-01-18","cited_by_count":8,"area":null},{"id":"2301.03136","title":"Removing Non-Stationary Knowledge From Pre-Trained Language Models for Entity-Level Sentiment Classification in Finance","created":"2023-01-09","cited_by_count":7,"area":null},{"id":"2306.16722","title":"Evaluating Paraphrastic Robustness in Textual Entailment Models","created":"2023-06-29","cited_by_count":7,"area":null},{"id":"2210.10689","title":"Towards Procedural Fairness: Uncovering Biases in How a Toxic Language Classifier Uses Sentiment Information","created":"2022-10-19","cited_by_count":6,"area":null},{"id":"2405.11891","title":"Unveiling and Manipulating Prompt Influence in Large Language Models","created":"2024-05-20","cited_by_count":6,"area":null},{"id":"2112.03057","title":"Thinking Beyond Distributions in Testing Machine Learned Models","created":"2021-12-06","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":"2305.09281","title":"On the Origins of Bias in NLP through the Lens of the Jim Code","created":"2023-05-16","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":"2211.11206","title":"Cultural Re-contextualization of Fairness Research in Language Technologies in India","created":"2022-11-21","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":"2106.07353","title":"Posthoc Verification and the Fallibility of the Ground Truth","created":"2021-06-02","cited_by_count":3,"area":null},{"id":"2202.03792","title":"Counterfactual Multi-Token Fairness in Text Classification","created":"2022-02-08","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":"2408.03732","title":"Question Rephrasing for Quantifying Uncertainty in Large Language Models: Applications in Molecular Chemistry Tasks","created":"2024-08-07","cited_by_count":3,"area":null},{"id":"2205.05050","title":"White-box Testing of NLP models with Mask Neuron Coverage","created":"2022-05-10","cited_by_count":2,"area":null},{"id":"2211.07047","title":"Language Model Classifier Aligns Better with Physician Word Sensitivity than XGBoost on Readmission Prediction","created":"2022-11-13","cited_by_count":2,"area":null},{"id":"2308.16549","title":"Thesis Distillation: Investigating The Impact of Bias in NLP Models on Hate Speech Detection","created":"2023-08-31","cited_by_count":2,"area":null},{"id":"2405.08468","title":"Challenges and Opportunities in Text Generation Explainability","created":"2024-05-14","cited_by_count":2,"area":null},{"id":"2408.00728","title":"CERT-ED: Certifiably Robust Text Classification for Edit Distance","created":"2024-08-01","cited_by_count":2,"area":null},{"id":"2109.07869","title":"Explainability Requires Interactivity","created":"2021-09-16","cited_by_count":1,"area":null},{"id":"2305.12829","title":"On Bias and Fairness in NLP: Investigating the Impact of Bias and Debiasing in Language Models on the Fairness of Toxicity Detection","created":"2023-05-22","cited_by_count":1,"area":null},{"id":"2305.13833","title":"Reducing Sensitivity on Speaker Names for Text Generation from Dialogues","created":"2023-05-23","cited_by_count":1,"area":null},{"id":"2508.04939","title":"I Think, Therefore I Am Under-Qualified? A Benchmark for Evaluating Linguistic Shibboleth Detection in LLM Hiring Evaluations","created":"2025-08-06","cited_by_count":1,"area":"lr"},{"id":"2112.00245","title":"True or False: Does the Deep Learning Model Learn to Detect Rumors?","created":"2021-12-01","cited_by_count":0,"area":null},{"id":"2303.15697","title":"Model and Evaluation: Towards Fairness in Multilingual Text Classification","created":"2023-03-28","cited_by_count":0,"area":null},{"id":"2311.04166","title":"Perturbed examples reveal invariances shared by language models","created":"2023-11-07","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":"2404.02068","title":"Using Interpretation Methods for Model Enhancement","created":"2024-04-02","cited_by_count":0,"area":null},{"id":"2404.19708","title":"Harmonic LLMs are Trustworthy","created":"2024-04-30","cited_by_count":0,"area":null},{"id":"2509.22291","title":"Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2601.16398","title":"White-Box Sensitivity Auditing with Steering Vectors","created":"2026-01-23","cited_by_count":0,"area":"mechinterp"},{"id":"2607.23680","title":"Perturbation-Aware Diffusion-Guided Hybrid Segmentation for Robust and Annotation-Efficient Plant Stress Phenotyping","created":"2026-07-26","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}