{"total":17,"rows":[{"id":"2402.07827","title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model","created":"2024-02-12","cited_by_count":295,"area":null},{"id":"2405.09373","title":"PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models","created":"2024-05-15","cited_by_count":20,"area":null},{"id":"2403.03893","title":"From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models","created":"2024-03-06","cited_by_count":18,"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":"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":"2503.05565","title":"Evaluating open-source Large Language Models for automated fact-checking","created":"2025-03-07","cited_by_count":6,"area":null},{"id":"2503.13390","title":"Aligned Probing: Relating Toxic Behavior and Model Internals","created":"2025-03-17","cited_by_count":5,"area":null},{"id":"2501.01256","title":"Digital Guardians: Can GPT-4, Perspective API, and Moderation API reliably detect hate speech in reader comments of German online newspapers?","created":"2025-01-02","cited_by_count":3,"area":null},{"id":"2412.04942","title":"A Federated Approach to Few-Shot Hate Speech Detection for Marginalized Communities","created":"2024-12-06","cited_by_count":2,"area":null},{"id":"2504.19594","title":"Mapping the Italian Telegram Ecosystem: Communities, Toxicity, and Hate Speech","created":"2025-04-28","cited_by_count":2,"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":"2504.12180","title":"Trusting CHATGPT: how minor tweaks in the prompts lead to major differences in sentiment classification","created":"2025-04-16","cited_by_count":0,"area":null},{"id":"2508.11061","title":"BIPOLAR: Polarization-based granular framework for LLM bias evaluation","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2601.06700","title":"Characterising Toxicity in Generative Large Language Models","created":"2026-01-10","cited_by_count":0,"area":null},{"id":"2603.01457","title":"Power Echoes: Investigating Moderation Biases in Online Power-Asymmetric Conflicts","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2605.04886","title":"BenCSSmark: Making the Social Sciences Count in LLM Research","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2610.16757","title":"Is the Platform Part of the Measurement? A Protocol and Simulation Study for Cross-Platform Equivalence of Machine-Labelled Policy Sentiment","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}