{"total":13,"rows":[{"id":"2405.15194","title":"Extracting Heuristics from Large Language Models for Reward Shaping in Reinforcement Learning","created":"2024-05-24","cited_by_count":8,"area":null},{"id":"2412.13698","title":"Towards Efficient and Explainable Hate Speech Detection via Model Distillation","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2601.03481","title":"Self-Explaining Hate Speech Detection with Moral Rationales","created":"2026-01-07","cited_by_count":5,"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":"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":"2511.07065","title":"Aligning Attention with Human Rationales for Self-Explaining Hate Speech Detection","created":"2025-11-10","cited_by_count":3,"area":null},{"id":"2506.19113","title":"Argument-Based Consistency in Toxicity Explanations of LLMs","created":"2025-06-23","cited_by_count":2,"area":null},{"id":"2404.11036","title":"Cross-Platform Hate Speech Detection with Weakly Supervised Causal Disentanglement","created":"2024-04-17","cited_by_count":1,"area":null},{"id":"2510.25805","title":"Ideology-Based LLMs for Content Moderation","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2409.14464","title":"AggregHate: An Efficient Aggregative Approach for the Detection of Hatemongers on Social Platforms","created":"2024-09-22","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":"2604.21667","title":"Fine-Grained Perspectives: Modeling Explanations with Annotator-Specific Rationales","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2608.27462","title":"Sledgehammer or Scalpel? A Fine-grained Adaptive Framework for Implicit Hate Speech","created":"2026-07-10","cited_by_count":0,"area":null}],"next_cursor":null}