{"total":20,"rows":[{"id":"2204.11788","title":"Human-AI Collaboration via Conditional Delegation: A Case Study of Content Moderation","created":"2022-04-25","cited_by_count":67,"area":null},{"id":"2501.15463","title":"Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?","created":"2025-01-26","cited_by_count":51,"area":null},{"id":"2504.14904","title":"VLM as Policy: Common-Law Content Moderation Framework for Short Video Platform","created":"2025-04-21","cited_by_count":21,"area":null},{"id":"2205.05738","title":"DISARM: Detecting the Victims Targeted by Harmful Memes","created":"2022-05-11","cited_by_count":20,"area":null},{"id":"2406.07353","title":"Toxic Memes: A Survey of Computational Perspectives on the Detection and Explanation of Meme Toxicities","created":"2024-06-11","cited_by_count":13,"area":null},{"id":"2411.01844","title":"DeMod: A Holistic Tool with Explainable Detection and Personalized Modification for Toxicity Censorship","created":"2024-11-04","cited_by_count":7,"area":null},{"id":"2310.16955","title":"Break it, Imitate it, Fix it: Robustness by Generating Human-Like Attacks","created":"2023-10-25","cited_by_count":5,"area":null},{"id":"2407.15227","title":"A Community-Centric Perspective for Characterizing and Detecting Anti-Asian Violence-Provoking Speech","created":"2024-07-21","cited_by_count":4,"area":null},{"id":"2411.19832","title":"Sensitive Content Classification in Social Media: A Holistic Resource and Evaluation","created":"2024-11-29","cited_by_count":4,"area":null},{"id":"2302.00102","title":"Towards Detecting Harmful Agendas in News Articles","created":"2023-01-31","cited_by_count":3,"area":null},{"id":"2509.25539","title":"Toxicity in Online Platforms and AI Systems: A Survey of Needs, Challenges, Mitigations, and Future Directions","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2504.08609","title":"A Survey of Machine Learning Models and Datasets for the Multi-label Classification of Textual Hate Speech in English","created":"2025-04-11","cited_by_count":2,"area":null},{"id":"2604.03920","title":"From Plausible to Causal: Counterfactual Semantics for Policy Evaluation in Simulated Online Communities","created":"2026-04-05","cited_by_count":2,"area":null},{"id":"2411.02594","title":"A Risk Taxonomy and Reflection Tool for Large Language Model Adoption in Public Health","created":"2024-11-04","cited_by_count":1,"area":null},{"id":"2403.14467","title":"Recourse for reclamation: Chatting with generative language models","created":"2024-03-21","cited_by_count":0,"area":null},{"id":"2405.11030","title":"The Unappreciated Role of Intent in Algorithmic Moderation of Social Media Content","created":"2024-05-17","cited_by_count":0,"area":null},{"id":"2504.16304","title":"MetaHarm: Harmful YouTube Video Dataset Annotated by Domain Experts, GPT-4-Turbo, and Crowdworkers","created":"2025-04-22","cited_by_count":0,"area":null},{"id":"2606.13397","title":"Mod-Guide: An LLM-based Content Moderation Feedback System to Address Insensitive Speech toward Indigenous Ethnic and Religious Minority Communities","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2607.05165","title":"Physiological Noise Augmentation Improves Non-Invasive Brain-to-Speech","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2609.35028","title":"VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformation","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}