{"total":41,"rows":[{"id":"2403.17752","title":"Can multiple-choice questions really be useful in detecting the abilities of LLMs?","created":"2024-03-26","cited_by_count":69,"area":null},{"id":"2408.03468","title":"MultiHateClip: A Multilingual Benchmark Dataset for Hateful Video Detection on YouTube and Bilibili","created":"2024-07-28","cited_by_count":25,"area":null},{"id":"2502.06207","title":"Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreement","created":"2025-02-10","cited_by_count":14,"area":null},{"id":"2410.02378","title":"Towards Comprehensive Detection of Chinese Harmful Memes","created":"2024-10-03","cited_by_count":13,"area":null},{"id":"2412.11691","title":"Multilingual and Explainable Text Detoxification with Parallel Corpora","created":"2024-12-16","cited_by_count":12,"area":null},{"id":"2505.24341","title":"Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings","created":"2025-05-30","cited_by_count":10,"area":null},{"id":"2507.07640","title":"Lost in Pronunciation: Detecting Chinese Offensive Language Disguised by Phonetic Cloaking Replacement","created":"2025-07-10","cited_by_count":10,"area":null},{"id":"2501.15451","title":"STATE ToxiCN: A Benchmark for Span-level Target-Aware Toxicity Extraction in Chinese Hate Speech Detection","created":"2025-01-26","cited_by_count":9,"area":null},{"id":"2312.16490","title":"Exploring news intent and its application: A theory-driven approach","created":"2023-12-27","cited_by_count":7,"area":null},{"id":"2501.15042","title":"SCCD: A Session-based Dataset for Chinese Cyberbullying Detection","created":"2025-01-25","cited_by_count":7,"area":null},{"id":"2505.12727","title":"What is Stigma Attributed to? A Theory-Grounded, Expert-Annotated Interview Corpus for Demystifying Mental-Health Stigma","created":"2025-05-19","cited_by_count":6,"area":null},{"id":"2510.00567","title":"Are Large Language Models Chronically Online Surfers? A Dataset for Chinese Internet Meme Explanation","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2403.18314","title":"Chinese Offensive Language Detection:Current Status and Future Directions","created":"2024-03-27","cited_by_count":5,"area":null},{"id":"2505.15773","title":"ToxicTone: A Mandarin Audio Dataset Annotated for Toxicity and Toxic Utterance Tonality","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2506.06347","title":"Unified Game Moderation: Soft-Prompting and LLM-Assisted Label Transfer for Resource-Efficient Toxicity Detection","created":"2025-06-01","cited_by_count":5,"area":null},{"id":"2307.05578","title":"Hate Speech Detection via Dual Contrastive Learning","created":"2023-07-10","cited_by_count":3,"area":null},{"id":"2411.19668","title":"ChineseWebText 2.0: Large-Scale High-quality Chinese Web Text with Multi-dimensional and fine-grained information","created":"2024-11-29","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":"2509.16660","title":"Redefining Experts: Interpretable Decomposition of Language Models for Toxicity Mitigation","created":"2025-09-20","cited_by_count":3,"area":null},{"id":"2409.05005","title":"Towards Patronizing and Condescending Language in Chinese Videos: A Multimodal Dataset and Detector","created":"2024-09-08","cited_by_count":2,"area":null},{"id":"2501.00697","title":"PANDA -- Paired Anti-hate Narratives Dataset from Asia: Using an LLM-as-a-Judge to Create the First Chinese Counterspeech Dataset","created":"2025-01-01","cited_by_count":2,"area":null},{"id":"2505.15297","title":"Chinese Toxic Language Mitigation via Sentiment Polarity Consistent Rewrites","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2506.04693","title":"Cracking the Code: Enhancing Implicit Hate Speech Detection through Coding Classification","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2506.08409","title":"FUSE: Measure-Theoretic Compact Fuzzy Set Representation for Taxonomy Expansion","created":"2025-06-10","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":"2604.15841","title":"Exploring the Capability Boundaries of LLMs in Mastering of Chinese Chouxiang Language","created":"2026-04-17","cited_by_count":2,"area":null},{"id":"2410.00361","title":"PclGPT: A Large Language Model for Patronizing and Condescending Language Detection","created":"2024-10-01","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":"2410.11230","title":"\"Is Hate Lost in Translation?\": Evaluation of Multilingual LGBTQIA+ Hate Speech Detection","created":"2024-10-15","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":"2601.06700","title":"Characterising Toxicity in Generative Large Language Models","created":"2026-01-10","cited_by_count":0,"area":null},{"id":"2601.13547","title":"HateXScore: A Metric Suite for Evaluating Reasoning Quality in Hate Speech Explanations","created":"2026-01-20","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":"2604.12321","title":"ToxiTrace: Gradient-Aligned Training for Explainable Chinese Toxicity Detection","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2606.07300","title":"Phun-Bench: Evaluating LLMs on Phonological Understanding in Chinese","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.27629","title":"Cross-Platform Chinese Offensive Comment Detection via Dual-Threshold Hard Example Mining","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.16790","title":"Cascading versus Joint Modeling for Hierarchical Offensive Language Detection","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2608.12361","title":"New Terms, New Toxicity: Consensus-based Chinese Neologism Toxicity Detection via Search-Augmented LLMs","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2608.22018","title":"SPAR-Hate: Auditor-Guided Multi-Perspective Role Reasoning for Bilingual Hate Speech Parsing","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2609.05843","title":"SinoGlyphBench: A Diagnostic Benchmark for Chinese Glyph-Level Obfuscation in Language-Model Moderation","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2610.14464","title":"Evaluating Bias in Chinese Large Language Models across Tasks and Registers: Task Operationalization Effects and Irony Classification Risks","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}