{"total":47,"rows":[{"id":"2308.01263","title":"XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models","created":"2023-08-02","cited_by_count":505,"area":null},{"id":"2202.11176","title":"A New Generation of Perspective API: Efficient Multilingual Character-level Transformers","created":"2022-02-22","cited_by_count":185,"area":null},{"id":"2302.08500","title":"Auditing large language models: a three-layered approach","created":"2023-02-16","cited_by_count":137,"area":null},{"id":"2504.08165","title":"Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora","created":"2025-04-10","cited_by_count":88,"area":null},{"id":"2405.03486","title":"UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images","created":"2024-05-06","cited_by_count":53,"area":null},{"id":"2206.09917","title":"Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models","created":"2022-06-20","cited_by_count":51,"area":null},{"id":"2303.04222","title":"SemEval-2023 Task 10: Explainable Detection of Online Sexism","created":"2023-03-07","cited_by_count":48,"area":null},{"id":"2204.14256","title":"Handling and Presenting Harmful Text in NLP Research","created":"2022-04-29","cited_by_count":43,"area":null},{"id":"2307.08153","title":"Analyzing Dataset Annotation Quality Management in the Wild","created":"2023-07-16","cited_by_count":41,"area":null},{"id":"2303.18190","title":"Assessing Language Model Deployment with Risk Cards","created":"2023-03-31","cited_by_count":30,"area":null},{"id":"2404.17874","title":"From Languages to Geographies: Towards Evaluating Cultural Bias in Hate Speech Datasets","created":"2024-04-27","cited_by_count":25,"area":null},{"id":"2302.05706","title":"MTTM: Metamorphic Testing for Textual Content Moderation Software","created":"2023-02-11","cited_by_count":22,"area":null},{"id":"2206.15455","title":"Hate Speech Criteria: A Modular Approach to Task-Specific Hate Speech Definitions","created":"2022-06-30","cited_by_count":18,"area":null},{"id":"2204.01906","title":"Dynatask: A Framework for Creating Dynamic AI Benchmark Tasks","created":"2022-04-05","cited_by_count":16,"area":null},{"id":"2501.16750","title":"HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns","created":"2025-01-28","cited_by_count":14,"area":null},{"id":"2206.13757","title":"Flexible text generation for counterfactual fairness probing","created":"2022-06-28","cited_by_count":13,"area":null},{"id":"2403.19559","title":"Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset","created":"2024-03-28","cited_by_count":13,"area":null},{"id":"2411.05214","title":"STAND-Guard: A Small Task-Adaptive Content Moderation Model","created":"2024-11-07","cited_by_count":12,"area":null},{"id":"2404.10710","title":"Autoregressive Pre-Training on Pixels and Texts","created":"2024-04-16","cited_by_count":10,"area":null},{"id":"2405.05418","title":"Mitigating Exaggerated Safety in Large Language Models","created":"2024-05-08","cited_by_count":8,"area":null},{"id":"2305.14384","title":"Adversarial Nibbler: A Data-Centric Challenge for Improving the Safety of Text-to-Image Models","created":"2023-05-22","cited_by_count":7,"area":null},{"id":"2305.13276","title":"Evaluating ChatGPT's Performance for Multilingual and Emoji-based Hate Speech Detection","created":"2023-05-22","cited_by_count":6,"area":null},{"id":"2311.01751","title":"EmojiLM: Modeling the New Emoji Language","created":"2023-11-03","cited_by_count":6,"area":null},{"id":"2305.13623","title":"Validating Multimedia Content Moderation Software via Semantic Fusion","created":"2023-05-23","cited_by_count":5,"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":"2308.09810","title":"An Image is Worth a Thousand Toxic Words: A Metamorphic Testing Framework for Content Moderation Software","created":"2023-08-18","cited_by_count":3,"area":null},{"id":"2402.15238","title":"GPT-HateCheck: Can LLMs Write Better Functional Tests for Hate Speech Detection?","created":"2024-02-23","cited_by_count":3,"area":null},{"id":"2406.04220","title":"BEADs: Bias Evaluation Across Domains","created":"2024-06-06","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":"2512.01899","title":"Provably Safe Model Updates","created":"2025-12-01","cited_by_count":3,"area":null},{"id":"2305.12951","title":"Cross-functional Analysis of Generalisation in Behavioural Learning","created":"2023-05-22","cited_by_count":2,"area":null},{"id":"2403.08425","title":"Specification Overfitting in Artificial Intelligence","created":"2024-03-13","cited_by_count":2,"area":null},{"id":"2507.11292","title":"Fine-Grained Chinese Hate Speech Understanding: Span-Level Resources, Coded Term Lexicon, and Enhanced Detection Frameworks","created":"2025-07-15","cited_by_count":2,"area":null},{"id":"2111.10497","title":"Combining Data-driven Supervision with Human-in-the-loop Feedback for Entity Resolution","created":"2021-11-20","cited_by_count":1,"area":null},{"id":"2505.22184","title":"Breaking the Cloak! Unveiling Chinese Cloaked Toxicity with Homophone Graph and Toxic Lexicon","created":"2025-05-28","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":"2210.08097","title":"TestAug: A Framework for Augmenting Capability-based NLP Tests","created":"2022-10-14","cited_by_count":0,"area":null},{"id":"2307.16811","title":"DoDo Learning: DOmain-DemOgraphic Transfer in Language Models for Detecting Abuse Targeted at Public Figures","created":"2023-07-31","cited_by_count":0,"area":null},{"id":"2311.08481","title":"Functionality learning through specification instructions","created":"2023-11-14","cited_by_count":0,"area":null},{"id":"2401.12989","title":"Into the crossfire: evaluating the use of a language model to crowdsource gun violence reports","created":"2024-01-16","cited_by_count":0,"area":null},{"id":"2503.14926","title":"Covering Cracks in Content Moderation: Delexicalized Distant Supervision for Illicit Drug Jargon Detection","created":"2025-03-19","cited_by_count":0,"area":null},{"id":"2504.17653","title":"Towards a comprehensive taxonomy of online abusive language informed by machine leaning","created":"2025-04-24","cited_by_count":0,"area":null},{"id":"2506.00583","title":"The Hidden Language of Harm: Examining the Role of Emojis in Harmful Online Communication and Content Moderation","created":"2025-05-31","cited_by_count":0,"area":null},{"id":"2506.16190","title":"Web(er) of Hate: A Survey on How Hate Speech Is Typed","created":"2025-06-19","cited_by_count":0,"area":null},{"id":"2509.24215","title":"Metamorphic Testing for Audio Content Moderation Software","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2603.14843","title":"ContiGuard: A Framework for Continual Toxicity Detection Against Evolving Evasive Perturbations","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2609.16900","title":"RiskChainBench: A Benchmark for Obfuscated Platform Message Restoration and Evidence-Grounded Web Investigation","created":"2026-09-15","cited_by_count":0,"area":null}],"next_cursor":null}