{"total":66,"rows":[{"id":"2309.16797","title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","created":"2023-09-28","cited_by_count":551,"area":"lr"},{"id":"2602.12275","title":"On-Policy Context Distillation for Language Models","created":"2026-02-12","cited_by_count":186,"area":"distill"},{"id":"2205.12685","title":"Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations","created":"2022-05-25","cited_by_count":116,"area":null},{"id":"2306.05949","title":"Evaluating the Social Impact of Generative AI Systems in Systems and Society","created":"2023-06-09","cited_by_count":92,"area":null},{"id":"2305.19148","title":"Mitigating Label Biases for In-context Learning","created":"2023-05-28","cited_by_count":89,"area":null},{"id":"2305.14264","title":"Active Learning Principles for In-Context Learning with Large Language Models","created":"2023-05-23","cited_by_count":54,"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":"2406.10504","title":"Task Facet Learning: A Structured Approach to Prompt Optimization","created":"2024-06-15","cited_by_count":19,"area":null},{"id":"2407.16695","title":"Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack","created":"2024-07-23","cited_by_count":19,"area":null},{"id":"2411.07446","title":"Efficient and Accurate Prompt Optimization: the Benefit of Memory in Exemplar-Guided Reflection","created":"2024-11-12","cited_by_count":18,"area":null},{"id":"2505.09666","title":"System Prompt Optimization with Meta-Learning","created":"2025-05-14","cited_by_count":18,"area":null},{"id":"2205.11315","title":"KOLD: Korean Offensive Language Dataset","created":"2022-05-23","cited_by_count":14,"area":null},{"id":"2401.06301","title":"Misconfidence-based Demonstration Selection for LLM In-Context Learning","created":"2024-01-12","cited_by_count":14,"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":"2202.09517","title":"Deep Learning for Hate Speech Detection: A Comparative Study","created":"2022-02-19","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":"2504.07157","title":"GAAPO: Genetic Algorithmic Applied to Prompt Optimization","created":"2025-04-09","cited_by_count":11,"area":null},{"id":"2410.13281","title":"BanTH: A Multi-label Hate Speech Detection Dataset for Transliterated Bangla","created":"2024-10-17","cited_by_count":10,"area":null},{"id":"2311.07115","title":"Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label Descriptions","created":"2023-11-13","cited_by_count":9,"area":null},{"id":"2410.19499","title":"Introducing MAPO: Momentum-Aided Gradient Descent Prompt Optimization","created":"2024-10-25","cited_by_count":9,"area":null},{"id":"2210.15870","title":"\"It's Not Just Hate'': A Multi-Dimensional Perspective on Detecting Harmful Speech Online","created":"2022-10-28","cited_by_count":7,"area":null},{"id":"2209.10876","title":"An Attention Matrix for Every Decision: Faithfulness-based Arbitration Among Multiple Attention-Based Interpretations of Transformers in Text Classification","created":"2022-09-22","cited_by_count":6,"area":null},{"id":"2406.11109","title":"Investigating Annotator Bias in Large Language Models for Hate Speech Detection","created":"2024-06-17","cited_by_count":6,"area":null},{"id":"2408.11879","title":"Beyond Labels: Aligning Large Language Models with Human-like Reasoning","created":"2024-08-20","cited_by_count":6,"area":"lr"},{"id":"2509.11361","title":"MAPGD: Multi-Agent Prompt Gradient Descent for Collaborative Prompt Optimization","created":"2025-09-14","cited_by_count":6,"area":"agents"},{"id":"2210.00910","title":"Hypothesis Engineering for Zero-Shot Hate Speech Detection","created":"2022-10-03","cited_by_count":4,"area":null},{"id":"2211.06053","title":"CoRAL: a Context-aware Croatian Abusive Language Dataset","created":"2022-11-11","cited_by_count":4,"area":null},{"id":"2401.15535","title":"Quantifying Stereotypes in Language","created":"2024-01-28","cited_by_count":4,"area":null},{"id":"2409.12425","title":"Zero-to-Strong Generalization: Eliciting Strong Capabilities of Large Language Models Iteratively without Gold Labels","created":"2024-09-19","cited_by_count":4,"area":null},{"id":"2512.18027","title":"CoPE: A Small Language Model for Steerable and Scalable Content Labeling","created":"2025-12-19","cited_by_count":4,"area":null},{"id":"2306.15745","title":"Identity Construction in a Misogynist Incels Forum","created":"2023-06-27","cited_by_count":3,"area":null},{"id":"2410.23605","title":"Dynamic Uncertainty Ranking: Enhancing Retrieval-Augmented In-Context Learning for Long-Tail Knowledge in LLMs","created":"2024-10-31","cited_by_count":3,"area":"rag"},{"id":"2502.00136","title":"A Checks-and-Balances Framework for Context-Aware Ethical AI Alignment","created":"2025-01-31","cited_by_count":3,"area":"alignment"},{"id":"2509.04500","title":"Context Engineering for Trustworthiness: Rescorla Wagner Steering Under Mixed and Inappropriate Contexts","created":"2025-09-02","cited_by_count":3,"area":null},{"id":"2510.08413","title":"Prompts Generalize with Low Data: Non-vacuous Generalization Bounds for Optimizing Prompts with More Informative Priors","created":"2025-10-09","cited_by_count":3,"area":null},{"id":"2511.10287","title":"OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models","created":"2025-11-13","cited_by_count":3,"area":"mllm"},{"id":"2606.11627","title":"When Context Returns: Toward Robust Internalization in On-Policy Distillation","created":"2026-06-10","cited_by_count":3,"area":"distill"},{"id":"2405.11465","title":"Effective In-Context Example Selection through Data Compression","created":"2024-05-19","cited_by_count":2,"area":null},{"id":"2409.05136","title":"MHS-STMA: Multimodal Hate Speech Detection via Scalable Transformer-Based Multilevel Attention Framework","created":"2024-09-08","cited_by_count":2,"area":null},{"id":"2411.19017","title":"A Survey on Automatic Online Hate Speech Detection in Low-Resource Languages","created":"2024-11-28","cited_by_count":2,"area":null},{"id":"2504.08609","title":"A Survey of Machine Learning Models and Datasets for the Multi-label Classification of Textual Hate Speech in English","created":"2025-04-11","cited_by_count":2,"area":null},{"id":"2510.04384","title":"LLM Based Bayesian Optimization for Prompt Search","created":"2025-10-05","cited_by_count":2,"area":null},{"id":"2511.21038","title":"Semantic Anchors in In-Context Learning: Why Small LLMs Cannot Flip Their Labels","created":"2025-11-26","cited_by_count":2,"area":null},{"id":"2602.05874","title":"xList-Hate: A Checklist-Based Framework for Interpretable and Generalizable Hate Speech Detection","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2212.03513","title":"Truthful Meta-Explanations for Local Interpretability of Machine Learning Models","created":"2022-12-07","cited_by_count":1,"area":null},{"id":"2305.12829","title":"On Bias and Fairness in NLP: Investigating the Impact of Bias and Debiasing in Language Models on the Fairness of Toxicity Detection","created":"2023-05-22","cited_by_count":1,"area":null},{"id":"2506.21613","title":"ChildGuard: A Specialized Dataset for Combatting Child-Targeted Hate Speech","created":"2025-06-21","cited_by_count":1,"area":null},{"id":"2507.10326","title":"Grammar-Guided Evolutionary Search for Discrete Prompt Optimisation","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2508.16603","title":"GreenTEA: Gradient Descent with Topic-modeling and Evolutionary Auto-prompting","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2508.17890","title":"UniAPO: Unified Multimodal Automated Prompt Optimization","created":"2025-08-25","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":"2210.09340","title":"Transferring Knowledge via Neighborhood-Aware Optimal Transport for Low-Resource Hate Speech Detection","created":"2022-10-17","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":"2406.04876","title":"HateDebias: On the Diversity and Variability of Hate Speech Debiasing","created":"2024-06-07","cited_by_count":0,"area":null},{"id":"2412.04046","title":"Hostility Detection in UK Politics: A Dataset on Online Abuse Targeting MPs","created":"2024-12-05","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":"2508.04638","title":"Can NLP Tackle Hate Speech in the Real World? Stakeholder-Informed Feedback and Survey on Counterspeech","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2508.16555","title":"Transfer Learning via Lexical Relatedness: A Sarcasm and Hate Speech Case Study","created":"2025-08-22","cited_by_count":0,"area":null},{"id":"2511.16122","title":"ELPO: Ensemble Learning Based Prompt Optimization for Large Language Models","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2511.23264","title":"BanglaSentNet: An Explainable Hybrid Deep Learning Framework for Multi-Aspect Sentiment Analysis with Cross-Domain Transfer Learning","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2512.17367","title":"Adversarially Robust Detection of Harmful Online Content: A Computational Design Science Approach","created":"2025-12-19","cited_by_count":0,"area":"safety"},{"id":"2605.10563","title":"ThreatCore: A Benchmark for Explicit and Implicit Threat Detection","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2607.20497","title":"From Errors to Rules: Iterative Prompt Optimization for Text Classification","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2608.23152","title":"Counter with Evidence! A Multi-Agent Memory Efficient Reasoning Framework for Hate Category Informed Counterspeech Generation","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.25605","title":"From Specialization to Generalization: Instruction-tuned LLMs for Robust Harmful Content Mitigation","created":"2026-08-26","cited_by_count":0,"area":"safety"},{"id":"2610.00928","title":"Efficient Task Adaptation in Large Language Models: A Survey of Weight-Based, Prompt-Based, and Embedding-Based Adaptations","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}