{"total":35,"rows":[{"id":"2302.08500","title":"Auditing large language models: a three-layered approach","created":"2023-02-16","cited_by_count":137,"area":null},{"id":"2212.09746","title":"Evaluating Human-Language Model Interaction","created":"2022-12-19","cited_by_count":92,"area":null},{"id":"2207.10062","title":"DataPerf: Benchmarks for Data-Centric AI Development","created":"2022-07-20","cited_by_count":90,"area":null},{"id":"2303.04222","title":"SemEval-2023 Task 10: Explainable Detection of Online Sexism","created":"2023-03-07","cited_by_count":48,"area":null},{"id":"2305.14663","title":"You Are What You Annotate: Towards Better Models through Annotator Representations","created":"2023-05-24","cited_by_count":40,"area":null},{"id":"2303.18190","title":"Assessing Language Model Deployment with Risk Cards","created":"2023-03-31","cited_by_count":30,"area":null},{"id":"2405.05378","title":"\"They are uncultured\": Unveiling Covert Harms and Social Threats in LLM Generated Conversations","created":"2024-05-08","cited_by_count":25,"area":null},{"id":"2403.20103","title":"NLP for Counterspeech against Hate: A Survey and How-To Guide","created":"2024-03-29","cited_by_count":22,"area":null},{"id":"2404.01651","title":"NLP Systems That Can't Tell Use from Mention Censor Counterspeech, but Teaching the Distinction Helps","created":"2024-04-02","cited_by_count":20,"area":null},{"id":"2310.06458","title":"Cultural Compass: Predicting Transfer Learning Success in Offensive Language Detection with Cultural Features","created":"2023-10-10","cited_by_count":18,"area":null},{"id":"2307.04761","title":"Understanding Counterspeech for Online Harm Mitigation","created":"2023-07-01","cited_by_count":17,"area":null},{"id":"2411.15462","title":"HateDay: Insights from a Global Hate Speech Dataset Representative of a Day on Twitter","created":"2024-11-23","cited_by_count":13,"area":null},{"id":"2310.18130","title":"DELPHI: Data for Evaluating LLMs' Performance in Handling Controversial Issues","created":"2023-10-27","cited_by_count":11,"area":null},{"id":"2410.03543","title":"Re-examining Sexism and Misogyny Classification with Annotator Attitudes","created":"2024-10-04","cited_by_count":8,"area":null},{"id":"2305.14384","title":"Adversarial Nibbler: A Data-Centric Challenge for Improving the Safety of Text-to-Image Models","created":"2023-05-22","cited_by_count":7,"area":null},{"id":"2410.08481","title":"Generation with Dynamic Vocabulary","created":"2024-10-11","cited_by_count":6,"area":null},{"id":"2510.10998","title":"ABLEIST: Intersectional Disability Bias in LLM-Generated Hiring Scenarios","created":"2025-10-13","cited_by_count":5,"area":null},{"id":"2605.00227","title":"Persona-Grounded Safety Evaluation of AI Companions in Multi-Turn Conversations","created":"2026-04-30","cited_by_count":4,"area":null},{"id":"2209.04409","title":"Trigger Warnings: Bootstrapping a Violence Detector for FanFiction","created":"2022-09-09","cited_by_count":3,"area":null},{"id":"2312.07228","title":"Toxic language detection: a systematic review of Arabic datasets","created":"2023-12-12","cited_by_count":3,"area":null},{"id":"2404.11845","title":"Challenging Negative Gender Stereotypes: A Study on the Effectiveness of Automated Counter-Stereotypes","created":"2024-04-18","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":"2506.00308","title":"MythTriage: Scalable Detection of Opioid Use Disorder Myths on a Video-Sharing Platform","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2506.05635","title":"IYKYK: Using language models to decode extremist cryptolects","created":"2025-06-05","cited_by_count":3,"area":null},{"id":"2305.18585","title":"Exploiting Explainability to Design Adversarial Attacks and Evaluate Attack Resilience in Hate-Speech Detection Models","created":"2023-05-29","cited_by_count":2,"area":null},{"id":"2511.20672","title":"MindSET: Advancing Mental Health Benchmarking through Large-Scale Social Media Data","created":"2025-11-14","cited_by_count":2,"area":null},{"id":"2306.03722","title":"Evaluating the Effectiveness of Natural Language Inference for Hate Speech Detection in Languages with Limited Labeled Data","created":"2023-06-06","cited_by_count":1,"area":null},{"id":"2404.09615","title":"If there's a Trigger Warning, then where's the Trigger? Investigating Trigger Warnings at the Passage Level","created":"2024-04-15","cited_by_count":1,"area":null},{"id":"2602.22404","title":"SAFARI: A Community-Engaged Approach and Dataset of Stereotype Resources in the Sub-Saharan African Context","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2307.16811","title":"DoDo Learning: DOmain-DemOgraphic Transfer in Language Models for Detecting Abuse Targeted at Public Figures","created":"2023-07-31","cited_by_count":0,"area":null},{"id":"2503.05357","title":"Improving Hate Speech Classification with Cross-Taxonomy Dataset Integration","created":"2025-03-07","cited_by_count":0,"area":null},{"id":"2505.17642","title":"A Survey on Stereotype Detection in Natural Language Processing","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2507.20614","title":"Before the Outrage: Challenges and Advances in Predicting Online Antisocial Behavior","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2604.12321","title":"ToxiTrace: Gradient-Aligned Training for Explainable Chinese Toxicity Detection","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2609.12653","title":"SWARM: A Multilingual Human-Annotated Dataset for Russian Propaganda Detection in Search Engine Results","created":"2026-09-11","cited_by_count":0,"area":null}],"next_cursor":null}