{"total":56,"rows":[{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512,"area":null},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843,"area":null},{"id":"2110.01691","title":"AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts","created":"2021-10-04","cited_by_count":268,"area":null},{"id":"2402.09283","title":"Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey","created":"2024-02-14","cited_by_count":130,"area":null},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2301.11924","title":"AI model GPT-3 (dis)informs us better than humans","created":"2023-01-23","cited_by_count":78,"area":null},{"id":"2305.14965","title":"Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks","created":"2023-05-24","cited_by_count":49,"area":"safety"},{"id":"2305.17680","title":"Evaluating GPT-3 Generated Explanations for Hateful Content Moderation","created":"2023-05-28","cited_by_count":46,"area":null},{"id":"2306.11932","title":"Opportunities and Risks of LLMs for Scalable Deliberation with Polis","created":"2023-06-20","cited_by_count":42,"area":null},{"id":"2308.05596","title":"You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content","created":"2023-08-10","cited_by_count":39,"area":null},{"id":"2307.10234","title":"SentimentGPT: Exploiting GPT for Advanced Sentiment Analysis and its Departure from Current Machine Learning","created":"2023-07-16","cited_by_count":38,"area":null},{"id":"2304.03728","title":"Interpretable Unified Language Checking","created":"2023-04-07","cited_by_count":26,"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":"2312.11518","title":"User Modeling in the Era of Large Language Models: Current Research and Future Directions","created":"2023-12-11","cited_by_count":18,"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":"2310.11867","title":"Evaluating the Fairness of Discriminative Foundation Models in Computer Vision","created":"2023-10-18","cited_by_count":12,"area":null},{"id":"2308.02080","title":"Causality Guided Disentanglement for Cross-Platform Hate Speech Detection","created":"2023-08-03","cited_by_count":9,"area":"safety"},{"id":"2311.09993","title":"Generative AI for Hate Speech Detection: Evaluation and Findings","created":"2023-11-16","cited_by_count":7,"area":null},{"id":"2505.19776","title":"Analyzing Political Bias in LLMs via Target-Oriented Sentiment Classification","created":"2025-05-26","cited_by_count":7,"area":null},{"id":"2304.11079","title":"Academic Writing with GPT-3.5: Reflections on Practices, Efficacy and Transparency","created":"2023-02-12","cited_by_count":6,"area":null},{"id":"2401.14626","title":"Towards Lifelong Scene Graph Generation with Knowledge-ware In-context Prompt Learning","created":"2024-01-26","cited_by_count":6,"area":null},{"id":"2404.14695","title":"MisgenderMender: A Community-Informed Approach to Interventions for Misgendering","created":"2024-04-23","cited_by_count":6,"area":null},{"id":"2409.03274","title":"Recent Advances in Attack and Defense Approaches of Large Language Models","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2403.11456","title":"HateCOT: An Explanation-Enhanced Dataset for Generalizable Offensive Speech Detection via Large Language Models","created":"2024-03-18","cited_by_count":5,"area":null},{"id":"2406.12800","title":"Supporting Human Raters with the Detection of Harmful Content using Large Language Models","created":"2024-06-18","cited_by_count":5,"area":"safety"},{"id":"2407.10995","title":"LionGuard: Building a Contextualized Moderation Classifier to Tackle Localized Unsafe Content","created":"2024-06-24","cited_by_count":5,"area":null},{"id":"2210.00910","title":"Hypothesis Engineering for Zero-Shot Hate Speech Detection","created":"2022-10-03","cited_by_count":4,"area":null},{"id":"2403.08035","title":"Harnessing Artificial Intelligence to Combat Online Hate: Exploring the Challenges and Opportunities of Large Language Models in Hate Speech Detection","created":"2024-03-12","cited_by_count":4,"area":null},{"id":"2404.17985","title":"Detection of Conspiracy Theories Beyond Keyword Bias in German-Language Telegram Using Large Language Models","created":"2024-04-27","cited_by_count":4,"area":null},{"id":"2507.10996","title":"Mario at EXIST 2025: A Simple Gateway to Effective Multilingual Sexism Detection","created":"2025-07-15","cited_by_count":4,"area":null},{"id":"2204.03542","title":"Leveraging pre-trained language models for conversational information seeking from text","created":"2022-03-31","cited_by_count":3,"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":"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":"2507.12372","title":"Web-Browsing LLMs Can Access Social Media Profiles and Infer User Demographics","created":"2025-07-16","cited_by_count":3,"area":null},{"id":"2508.01712","title":"HateClipSeg: A Segment-Level Annotated Dataset for Fine-Grained Hate Video Detection","created":"2025-08-03","cited_by_count":3,"area":null},{"id":"2309.11896","title":"Focal Inferential Infusion Coupled with Tractable Density Discrimination for Implicit Hate Detection","created":"2023-09-21","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":"2506.03458","title":"Culture Matters in Toxic Language Detection in Persian","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2511.13759","title":"Multi-Agent VLMs Guided Self-Training with PNU Loss for Low-Resource Offensive Content Detection","created":"2025-11-14","cited_by_count":2,"area":"agents"},{"id":"2106.14720","title":"What's in a Measurement? Using GPT-3 on SemEval 2021 Task 8 -- MeasEval","created":"2021-06-28","cited_by_count":1,"area":null},{"id":"2112.07041","title":"Survey of Generative Methods for Social Media Analysis","created":"2021-12-13","cited_by_count":1,"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":"2311.00223","title":"Is GPT Powerful Enough to Analyze the Emotions of Memes?","created":"2023-11-01","cited_by_count":1,"area":null},{"id":"2312.02532","title":"DRAFT: Dense Retrieval Augmented Few-shot Topic classifier Framework","created":"2023-12-05","cited_by_count":1,"area":"rag"},{"id":"2402.14200","title":"Towards Understanding Counseling Conversations: Domain Knowledge and Large Language Models","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2403.02121","title":"Leveraging Weakly Annotated Data for Hate Speech Detection in Code-Mixed Hinglish: A Feasibility-Driven Transfer Learning Approach with Large Language Models","created":"2024-03-04","cited_by_count":1,"area":null},{"id":"2404.01822","title":"A (More) Realistic Evaluation Setup for Generalisation of Community Models on Malicious Content Detection","created":"2024-04-02","cited_by_count":1,"area":null},{"id":"2412.19928","title":"Assessing Text Classification Methods for Cyberbullying Detection on Social Media Platforms","created":"2024-12-27","cited_by_count":1,"area":null},{"id":"2504.01902","title":"Graphically Speaking: Unmasking Abuse in Social Media with Conversation Insights","created":"2025-04-02","cited_by_count":1,"area":null},{"id":"2312.13961","title":"ChatGPT as a commenter to the news: can LLMs generate human-like opinions?","created":"2023-12-21","cited_by_count":0,"area":null},{"id":"2411.09214","title":"HateGPT: Unleashing GPT-3.5 Turbo to Combat Hate Speech on X","created":"2024-11-14","cited_by_count":0,"area":null},{"id":"2505.20963","title":"Context-Aware Content Moderation for German Newspaper Comments","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2510.15685","title":"Leveraging LLMs for Context-Aware Implicit Textual and Multimodal Hate Speech Detection","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2512.02845","title":"Bangla Hate Speech Classification with Fine-tuned Transformer Models","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2605.20584","title":"QwenSafe: Multimodal Content Rating Description Identification via Preference-Aligned VLMs","created":"2026-05-20","cited_by_count":0,"area":"mllm"},{"id":"2605.27375","title":"LCO: LLM-based Constraint Optimization for Safer Agentic LLMs in Real-world Tasks","created":"2026-04-08","cited_by_count":0,"area":"agents"}],"next_cursor":null}