{"total":42,"rows":[{"id":"2402.10426","title":"DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection","created":"2024-02-16","cited_by_count":41,"area":null},{"id":"2409.03219","title":"Content Moderation by LLM: From Accuracy to Legitimacy","created":"2024-09-05","cited_by_count":30,"area":null},{"id":"2402.00371","title":"What Does the Bot Say? Opportunities and Risks of Large Language Models in Social Media Bot Detection","created":"2024-02-01","cited_by_count":25,"area":null},{"id":"2410.02657","title":"Hate Personified: Investigating the role of LLMs in content moderation","created":"2024-10-03","cited_by_count":25,"area":null},{"id":"2505.16491","title":"LLaMAs Have Feelings Too: Unveiling Sentiment and Emotion Representations in LLaMA Models Through Probing","created":"2025-05-22","cited_by_count":15,"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":"2411.10954","title":"Dialectal Toxicity Detection: Evaluating LLM-as-a-Judge Consistency Across Language Varieties","created":"2024-11-17","cited_by_count":12,"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":"2404.10464","title":"DESTEIN: Navigating Detoxification of Language Models via Universal Steering Pairs and Head-wise Activation Fusion","created":"2024-04-16","cited_by_count":9,"area":null},{"id":"2410.03543","title":"Re-examining Sexism and Misogyny Classification with Annotator Attitudes","created":"2024-10-04","cited_by_count":8,"area":null},{"id":"2505.06149","title":"Can Prompting LLMs Unlock Hate Speech Detection across Languages? A Zero-shot and Few-shot Study","created":"2025-05-09","cited_by_count":7,"area":null},{"id":"2410.00775","title":"Decoding Hate: Exploring Language Models' Reactions to Hate Speech","created":"2024-10-01","cited_by_count":6,"area":null},{"id":"2603.02913","title":"Eliciting Numerical Predictive Distributions of LLMs Without Autoregression","created":"2026-03-03","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":"2409.14673","title":"Instruction Tuning Vs. In-Context Learning: Revisiting Large Language Models in Few-Shot Computational Social Science","created":"2024-09-23","cited_by_count":5,"area":null},{"id":"2503.07237","title":"LLM-C3MOD: A Human-LLM Collaborative System for Cross-Cultural Hate Speech Moderation","created":"2025-03-10","cited_by_count":5,"area":null},{"id":"2508.08274","title":"Distilling Knowledge from Large Language Models: A Concept Bottleneck Model for Hate and Counter Speech Recognition","created":"2025-07-30","cited_by_count":5,"area":null},{"id":"2406.07886","title":"Label-aware Hard Negative Sampling Strategies with Momentum Contrastive Learning for Implicit Hate Speech Detection","created":"2024-06-12","cited_by_count":4,"area":null},{"id":"2409.09741","title":"Benchmarking LLMs in Political Content Text-Annotation: Proof-of-Concept with Toxicity and Incivility Data","created":"2024-09-15","cited_by_count":4,"area":null},{"id":"2502.19612","title":"Evaluation of Hate Speech Detection Using Large Language Models and Geographical Contextualization","created":"2025-02-26","cited_by_count":3,"area":null},{"id":"2509.18293","title":"Evaluating Large Language Models for Detecting Antisemitism","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2401.09244","title":"Cross-lingual Offensive Language Detection: A Systematic Review of Datasets, Transfer Approaches and Challenges","created":"2024-01-17","cited_by_count":2,"area":null},{"id":"2510.11167","title":"Bridging Gaps in Hate Speech Detection: Meta-Collections and Benchmarks for Low-Resource Iberian Languages","created":"2025-10-13","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":"2410.12174","title":"Exploring Large Language Models for Hate Speech Detection in Rioplatense Spanish","created":"2024-10-16","cited_by_count":1,"area":null},{"id":"2508.02502","title":"From Monolingual to Bilingual: Investigating Language Conditioning in Large Language Models for Psycholinguistic Tasks","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2508.21084","title":"Mapping Toxic Comments Across Demographics: A Dataset from German Public Broadcasting","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2510.20612","title":"Black Box Absorption: LLMs Undermining Innovative Ideas","created":"2025-10-23","cited_by_count":1,"area":null},{"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":"2601.03194","title":"X-MuTeST: A Multilingual Benchmark for Explainable Hate Speech Detection and A Novel LLM-consulted Explanation Framework","created":"2026-01-06","cited_by_count":1,"area":null},{"id":"2406.04876","title":"HateDebias: On the Diversity and Variability of Hate Speech Debiasing","created":"2024-06-07","cited_by_count":0,"area":null},{"id":"2503.18273","title":"Decoding Islamophobic Discourse: Using LLMs to Identify Tropes and Semi-Coded Hate Speech","created":"2025-03-24","cited_by_count":0,"area":null},{"id":"2506.09992","title":"Large Language Models for Toxic Language Detection in Low-Resource Balkan Languages","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2506.22491","title":"PromptAug: Fine-grained Conflict Classification Using Data Augmentation","created":"2025-06-24","cited_by_count":0,"area":null},{"id":"2509.15174","title":"SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2509.22291","title":"Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?","created":"2025-09-26","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":"2511.03128","title":"From Insight to Exploit: Leveraging LLM Collaboration for Adaptive Adversarial Text Generation","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2601.06907","title":"Fine-grained Verbal Attack Detection via a Hierarchical Divide-and-Conquer Framework","created":"2026-01-11","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":"2604.16845","title":"DART: Mitigating Harm Drift in Difference-Aware LLMs via Distill-Audit-Repair Training","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2605.27584","title":"Cyberbullying Governance on Social Media: A Unified Framework from Content Identification to Intervention","created":"2026-05-26","cited_by_count":0,"area":null}],"next_cursor":null}