{"total":26,"rows":[{"id":"2312.02003","title":"A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly","created":"2023-12-04","cited_by_count":387,"area":null},{"id":"2405.06823","title":"PLeak: Prompt Leaking Attacks against Large Language Model Applications","created":"2024-05-10","cited_by_count":127,"area":null},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"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":"2401.03346","title":"An Investigation of Large Language Models for Real-World Hate Speech Detection","created":"2024-01-07","cited_by_count":20,"area":null},{"id":"2407.15366","title":"Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias","created":"2024-07-22","cited_by_count":17,"area":null},{"id":"2309.14517","title":"Watch Your Language: Investigating Content Moderation with Large Language Models","created":"2023-09-25","cited_by_count":14,"area":null},{"id":"2404.02037","title":"MultiParaDetox: Extending Text Detoxification with Parallel Data to New Languages","created":"2024-04-02","cited_by_count":14,"area":null},{"id":"2310.19626","title":"Transformation vs Tradition: Artificial General Intelligence (AGI) for Arts and Humanities","created":"2023-10-30","cited_by_count":9,"area":null},{"id":"2506.16393","title":"From LLM-anation to LLM-orchestrator: Coordinating Small Models for Data Labeling","created":"2025-06-19","cited_by_count":8,"area":null},{"id":"2406.03363","title":"LLM-based Rewriting of Inappropriate Argumentation using Reinforcement Learning from Machine Feedback","created":"2024-06-05","cited_by_count":7,"area":null},{"id":"2408.05941","title":"Multimodal Large Language Models for Phishing Webpage Detection and Identification","created":"2024-08-12","cited_by_count":7,"area":null},{"id":"2509.07287","title":"Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigm","created":"2025-09-08","cited_by_count":5,"area":null},{"id":"2403.02472","title":"OffensiveLang: A Community Based Implicit Offensive Language Dataset","created":"2024-03-04","cited_by_count":3,"area":null},{"id":"2508.11281","title":"ToxiFrench: Benchmarking and Enhancing Language Models via CoT Fine-Tuning for French Toxicity Detection","created":"2025-08-15","cited_by_count":3,"area":null},{"id":"2506.02326","title":"Something Just Like TRuST : Toxicity Recognition of Span and Target","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2506.03009","title":"Conditioning Large Language Models on Legal Systems? Detecting Punishable Hate Speech","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2506.19113","title":"Argument-Based Consistency in Toxicity Explanations of LLMs","created":"2025-06-23","cited_by_count":2,"area":null},{"id":"2410.06427","title":"NLP Case Study on Predicting the Before and After of the Ukraine-Russia and Hamas-Israel Conflicts","created":"2024-10-08","cited_by_count":1,"area":null},{"id":"2410.14894","title":"Soft-Label Integration for Robust Toxicity Classification","created":"2024-10-18","cited_by_count":1,"area":null},{"id":"2411.07527","title":"Prompt-enhanced Network for Hateful Meme Classification","created":"2024-11-12","cited_by_count":1,"area":null},{"id":"2505.23386","title":"VModA: An Effective Framework for Adaptive NSFW Image Moderation","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2508.20514","title":"SciTopic: Enhancing Topic Discovery in Scientific Literature through Advanced LLM","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2404.02205","title":"A Holistic Indicator of Polarization to Measure Online Sexism","created":"2024-04-02","cited_by_count":0,"area":null},{"id":"2602.15866","title":"NLP Privacy Risk Identification in Social Media (NLP-PRISM): A Survey","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2604.12770","title":"Teaching LLMs Human-Like Editing of Inappropriate Argumentation via Reinforcement Learning","created":"2026-04-14","cited_by_count":0,"area":null}],"next_cursor":null}