{"total":68,"rows":[{"id":"2211.02570","title":"The 'Problem' of Human Label Variation: On Ground Truth in Data, Modeling and Evaluation","created":"2022-11-04","cited_by_count":139,"area":null},{"id":"2104.06390","title":"Detoxifying Language Models Risks Marginalizing Minority Voices","created":"2021-04-13","cited_by_count":107,"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":"2307.01680","title":"Robust Hate Speech Detection in Social Media: A Cross-Dataset Empirical Evaluation","created":"2023-07-04","cited_by_count":28,"area":null},{"id":"2311.08685","title":"Safer-Instruct: Aligning Language Models with Automated Preference Data","created":"2023-11-15","cited_by_count":27,"area":"alignment"},{"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":"2210.10839","title":"How Hate Speech Varies by Target Identity: A Computational Analysis","created":"2022-10-19","cited_by_count":23,"area":null},{"id":"2310.19660","title":"Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneck","created":"2023-10-30","cited_by_count":22,"area":null},{"id":"2307.04761","title":"Understanding Counterspeech for Online Harm Mitigation","created":"2023-07-01","cited_by_count":17,"area":null},{"id":"2403.12403","title":"Towards Interpretable Hate Speech Detection using Large Language Model-extracted Rationales","created":"2024-03-19","cited_by_count":16,"area":null},{"id":"2401.06526","title":"MetaHate: A Dataset for Unifying Efforts on Hate Speech Detection","created":"2024-01-12","cited_by_count":14,"area":null},{"id":"2402.16979","title":"Algorithmic Arbitrariness in Content Moderation","created":"2024-02-26","cited_by_count":13,"area":null},{"id":"2408.15488","title":"Legilimens: Practical and Unified Content Moderation for Large Language Model Services","created":"2024-08-28","cited_by_count":13,"area":"safety"},{"id":"2404.10857","title":"D3CODE: Disentangling Disagreements in Data across Cultures on Offensiveness Detection and Evaluation","created":"2024-04-16","cited_by_count":11,"area":null},{"id":"2403.04085","title":"Don't Blame the Data, Blame the Model: Understanding Noise and Bias When Learning from Subjective Annotations","created":"2024-03-06","cited_by_count":10,"area":null},{"id":"2411.10461","title":"Utilizing Human Behavior Modeling to Manipulate Explanations in AI-Assisted Decision Making: The Good, the Bad, and the Scary","created":"2024-11-02","cited_by_count":10,"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":"2405.17512","title":"On Fairness of Low-Rank Adaptation of Large Models","created":"2024-05-27","cited_by_count":9,"area":null},{"id":"2409.02078","title":"Political DEBATE: Efficient Zero-shot and Few-shot Classifiers for Political Text","created":"2024-09-03","cited_by_count":8,"area":null},{"id":"2406.00046","title":"Hate Speech Detection with Generalizable Target-aware Fairness","created":"2024-05-28","cited_by_count":7,"area":null},{"id":"2410.15911","title":"DefVerify: Do Hate Speech Models Reflect Their Dataset's Definition?","created":"2024-10-21","cited_by_count":7,"area":null},{"id":"2306.08804","title":"PEACE: Cross-Platform Hate Speech Detection- A Causality-guided Framework","created":"2023-06-15","cited_by_count":6,"area":null},{"id":"2405.08562","title":"The Unseen Targets of Hate -- A Systematic Review of Hateful Communication Datasets","created":"2024-05-14","cited_by_count":6,"area":null},{"id":"2312.06034","title":"Modeling Uncertainty in Personalized Emotion Prediction with Normalizing Flows","created":"2023-12-10","cited_by_count":5,"area":null},{"id":"2206.13284","title":"Which one is more toxic? Findings from Jigsaw Rate Severity of Toxic Comments","created":"2022-06-27","cited_by_count":4,"area":null},{"id":"2508.07063","title":"Towards Safer AI Moderation: Evaluating LLM Moderators Through a Unified Benchmark Dataset and Advocating a Human-First Approach","created":"2025-08-09","cited_by_count":4,"area":null},{"id":"2505.24262","title":"On Fairness of Task Arithmetic: The Role of Task Vectors","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2305.18585","title":"Exploiting Explainability to Design Adversarial Attacks and Evaluate Attack Resilience in Hate-Speech Detection Models","created":"2023-05-29","cited_by_count":2,"area":null},{"id":"2312.08198","title":"Towards Model-Based Data Acquisition for Subjective Multi-Task NLP Problems","created":"2023-12-13","cited_by_count":2,"area":null},{"id":"2404.01785","title":"Can Humans Identify Domains?","created":"2024-04-02","cited_by_count":2,"area":null},{"id":"2410.18749","title":"Does Differential Privacy Impact Bias in Pretrained NLP Models?","created":"2024-10-24","cited_by_count":2,"area":null},{"id":"2505.14272","title":"Data-Efficient Hate Speech Detection via Cross-Lingual Nearest Neighbor Retrieval with Limited Labeled Data","created":"2025-05-20","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":"2506.13513","title":"K/DA: Automated Data Generation Pipeline for Detoxifying Implicitly Offensive Language in Korean","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2506.14569","title":"Enhancing Symbolic Machine Learning by Subsymbolic Representations","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2307.08945","title":"Mitigating Label Bias via Decoupled Confident Learning","created":"2023-07-18","cited_by_count":1,"area":null},{"id":"2409.09613","title":"Rethinking KenLM: Good and Bad Model Ensembles for Efficient Text Quality Filtering in Large Web Corpora","created":"2024-09-15","cited_by_count":1,"area":"lr"},{"id":"2506.14903","title":"DETONATE: A Benchmark for Text-to-Image Alignment and Kernelized Direct Preference Optimization","created":"2025-06-17","cited_by_count":1,"area":"diffusion"},{"id":"2512.09662","title":"Can LLMs Evaluate What They Cannot Annotate? Revisiting LLM Reliability in Hate Speech Detection","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2604.18069","title":"Modeling Human Perspectives with Socio-Demographic Representations","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2605.01168","title":"Quantifying and Predicting Disagreement in Graded Human Ratings","created":"2026-05-01","cited_by_count":1,"area":null},{"id":"2605.27025","title":"Attribute-Based Diagnosis of LLM Alignment with Hate Speech Annotations","created":"2026-05-26","cited_by_count":1,"area":"alignment"},{"id":"2104.10807","title":"COVID-19 and Big Data: Multi-faceted Analysis for Spatio-temporal Understanding of the Pandemic with Social Media Conversations","created":"2021-04-22","cited_by_count":0,"area":null},{"id":"2210.16398","title":"System Demo: Tool and Infrastructure for Offensive Language Error Analysis (OLEA) in English","created":"2022-10-28","cited_by_count":0,"area":null},{"id":"2306.03907","title":"CL-UZH at SemEval-2023 Task 10: Sexism Detection through Incremental Fine-Tuning and Multi-Task Learning with Label Descriptions","created":"2023-06-06","cited_by_count":0,"area":null},{"id":"2306.05075","title":"LCT-1 at SemEval-2023 Task 10: Pre-training and Multi-task Learning for Sexism Detection and Classification","created":"2023-06-08","cited_by_count":0,"area":null},{"id":"2309.02912","title":"On the Challenges of Building Datasets for Hate Speech Detection","created":"2023-09-06","cited_by_count":0,"area":null},{"id":"2312.13193","title":"HCDIR: End-to-end Hate Context Detection, and Intensity Reduction model for online comments","created":"2023-12-20","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":"2407.06422","title":"Exploring the Capability of ChatGPT to Reproduce Human Labels for Social Computing Tasks (Extended Version)","created":"2024-07-08","cited_by_count":0,"area":null},{"id":"2407.12018","title":"Empirical Evaluation of Public HateSpeech Datasets","created":"2024-06-27","cited_by_count":0,"area":null},{"id":"2407.20377","title":"Leveraging Natural Language and Item Response Theory Models for ESG Scoring","created":"2024-07-29","cited_by_count":0,"area":null},{"id":"2410.08053","title":"A Target-Aware Analysis of Data Augmentation for Hate Speech Detection","created":"2024-10-10","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":"2507.07216","title":"Bias-Aware Mislabeling Detection via Decoupled Confident Learning","created":"2025-07-09","cited_by_count":0,"area":null},{"id":"2507.20614","title":"Before the Outrage: Challenges and Advances in Predicting Online Antisocial Behavior","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2508.09544","title":"SYNAPSE-G: Bridging Large Language Models and Graph Learning for Rare Event Classification","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2510.22405","title":"Knowledge-guided Continual Learning for Behavioral Analytics Systems","created":"2025-10-25","cited_by_count":0,"area":null},{"id":"2601.04207","title":"Ideology as a Problem: Lightweight Logit Steering for Annotator-Specific Alignment in Social Media Analysis","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2604.03796","title":"When AI Agents Disagree Like Humans: Reasoning Trace Analysis for Human-AI Collaborative Moderation","created":"2026-04-04","cited_by_count":0,"area":"lr"},{"id":"2605.01416","title":"Who Decides What Is Harmful? Content Moderation Policy Through A Multi-Agent Personalised Inference Framework","created":"2026-05-02","cited_by_count":0,"area":"agents"},{"id":"2605.11954","title":"Assessing and Mitigating Miscalibration in LLM-Based Social Science Measurement","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.27313","title":"When Does Demographic Information Help? Data and Modeling Regimes for Perspective-Aware Hate Speech Detection","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2605.27322","title":"Semantic Gradients Interactions in SSD: A Case Study in Racial Identity and Hate Speech","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.04223","title":"Consensus is Strategically Insufficient: Reasoning-Trace Disagreement as a Knowledge-Representation Signal","created":"2026-06-02","cited_by_count":0,"area":"lr"},{"id":"2606.06266","title":"From Self to Other: Evaluating Demographic Perspective-Taking in LLM Hate Speech Annotation","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2608.03675","title":"VetScore: Risk-Weighted Fact Verification for Veterinary Long-Form QA with Citations","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2610.18588","title":"Decomposing and Predicting Annotation Disagreement in Harmful Content Across Languages","created":"2026-10-13","cited_by_count":0,"area":"safety"}],"next_cursor":null}