{"total":22,"rows":[{"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":"2401.16727","title":"Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Models","created":"2024-01-30","cited_by_count":26,"area":null},{"id":"2402.06900","title":"Can LLMs Recognize Toxicity? A Structured Investigation Framework and Toxicity Metric","created":"2024-02-10","cited_by_count":23,"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":"2407.06908","title":"Divine LLaMAs: Bias, Stereotypes, Stigmatization, and Emotion Representation of Religion in Large Language Models","created":"2024-07-09","cited_by_count":12,"area":null},{"id":"2410.15911","title":"DefVerify: Do Hate Speech Models Reflect Their Dataset's Definition?","created":"2024-10-21","cited_by_count":7,"area":null},{"id":"2503.01030","title":"Language Models Predict Empathy Gaps Between Social In-groups and Out-groups","created":"2025-03-02","cited_by_count":6,"area":null},{"id":"2306.15745","title":"Identity Construction in a Misogynist Incels Forum","created":"2023-06-27","cited_by_count":3,"area":null},{"id":"2310.02876","title":"Hate Speech Detection in Limited Data Contexts using Synthetic Data Generation","created":"2023-10-04","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":"2410.16520","title":"AUTALIC: A Dataset for Anti-AUTistic Ableist Language In Context","created":"2024-10-21","cited_by_count":3,"area":null},{"id":"2510.19331","title":"Algorithmic Fairness in NLP: Persona-Infused LLMs for Human-Centric Hate Speech Detection","created":"2025-10-22","cited_by_count":2,"area":null},{"id":"2306.15732","title":"A Weakly Supervised Classifier and Dataset of White Supremacist Language","created":"2023-06-27","cited_by_count":1,"area":null},{"id":"2311.14865","title":"Improving Cross-Domain Hate Speech Generalizability with Emotion Knowledge","created":"2023-11-24","cited_by_count":1,"area":null},{"id":"2410.11647","title":"Measuring Spiritual Values and Bias of Large Language Models","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2410.20490","title":"Who Speaks Matters: Analysing the Influence of the Speaker's Ethnicity on Hate Classification","created":"2024-10-27","cited_by_count":1,"area":null},{"id":"2506.03916","title":"Compositional Generalisation for Explainable Hate Speech Detection","created":"2025-06-04","cited_by_count":1,"area":null},{"id":"2510.25805","title":"Ideology-Based LLMs for Content Moderation","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2604.25580","title":"Bye Bye Perspective API: Lessons for Building and Governing Measurement Infrastructure","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2510.22405","title":"Knowledge-guided Continual Learning for Behavioral Analytics Systems","created":"2025-10-25","cited_by_count":0,"area":null},{"id":"2601.09342","title":"Improving Implicit Hate Speech Detection via a Community-Driven Multi-Agent Framework","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2609.08637","title":"Navigating the digital spectrum: Assessing political bias, stability, and downstream fairness in Large Language Models","created":"2026-09-08","cited_by_count":0,"area":null}],"next_cursor":null}