{"total":171,"rows":[{"id":"2312.06674","title":"Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations","created":"2023-12-07","cited_by_count":1207,"area":null},{"id":"2110.15943","title":"MetaICL: Learning to Learn In Context","created":"2021-10-29","cited_by_count":454,"area":null},{"id":"2203.09509","title":"ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection","created":"2022-03-17","cited_by_count":422,"area":null},{"id":"2208.03274","title":"A Holistic Approach to Undesired Content Detection in the Real World","created":"2022-08-05","cited_by_count":356,"area":null},{"id":"2109.05322","title":"Latent Hatred: A Benchmark for Understanding Implicit Hate Speech","created":"2021-09-11","cited_by_count":217,"area":null},{"id":"2302.07736","title":"Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech","created":"2023-02-11","cited_by_count":166,"area":null},{"id":"2104.08835","title":"CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP","created":"2021-04-18","cited_by_count":142,"area":null},{"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":"2306.04618","title":"Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations","created":"2023-06-07","cited_by_count":97,"area":null},{"id":"2211.13972","title":"Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?","created":"2022-11-25","cited_by_count":91,"area":null},{"id":"2305.19148","title":"Mitigating Label Biases for In-context Learning","created":"2023-05-28","cited_by_count":89,"area":null},{"id":"2107.08720","title":"Human-in-the-Loop for Data Collection: a Multi-Target Counter Narrative Dataset to Fight Online Hate Speech","created":"2021-07-19","cited_by_count":82,"area":null},{"id":"2106.11410","title":"A Survey of Race, Racism, and Anti-Racism in NLP","created":"2021-06-21","cited_by_count":75,"area":null},{"id":"2102.08886","title":"Towards generalisable hate speech detection: a review on obstacles and solutions","created":"2021-02-17","cited_by_count":66,"area":null},{"id":"2202.00126","title":"Handling Bias in Toxic Speech Detection: A Survey","created":"2022-01-26","cited_by_count":61,"area":null},{"id":"2211.00151","title":"A Close Look into the Calibration of Pre-trained Language Models","created":"2022-10-31","cited_by_count":57,"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":"2307.12375","title":"In-Context Learning Learns Label Relationships but Is Not Conventional Learning","created":"2023-07-23","cited_by_count":51,"area":null},{"id":"2103.01664","title":"Hate Towards the Political Opponent: A Twitter Corpus Study of the 2020 US Elections on the Basis of Offensive Speech and Stance Detection","created":"2021-03-02","cited_by_count":45,"area":null},{"id":"2308.16705","title":"Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysis","created":"2023-08-31","cited_by_count":45,"area":null},{"id":"2305.15225","title":"SAIL: Search-Augmented Instruction Learning","created":"2023-05-24","cited_by_count":33,"area":null},{"id":"2112.08802","title":"UNIREX: A Unified Learning Framework for Language Model Rationale Extraction","created":"2021-12-16","cited_by_count":32,"area":null},{"id":"2310.09130","title":"Split-and-Denoise: Protect large language model inference with local differential privacy","created":"2023-10-13","cited_by_count":32,"area":null},{"id":"2311.09090","title":"Social Bias Probing: Fairness Benchmarking for Language Models","created":"2023-11-15","cited_by_count":32,"area":null},{"id":"2305.12696","title":"Learning Interpretable Style Embeddings via Prompting LLMs","created":"2023-05-22","cited_by_count":30,"area":null},{"id":"2103.10415","title":"Refining Language Models with Compositional Explanations","created":"2021-03-18","cited_by_count":27,"area":null},{"id":"2106.00742","title":"A systematic review of Hate Speech automatic detection using Natural Language Processing","created":"2021-05-22","cited_by_count":27,"area":null},{"id":"2111.01515","title":"Detection of Hate Speech using BERT and Hate Speech Word Embedding with Deep Model","created":"2021-11-02","cited_by_count":26,"area":null},{"id":"2304.03728","title":"Interpretable Unified Language Checking","created":"2023-04-07","cited_by_count":26,"area":null},{"id":"2401.16727","title":"Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Models","created":"2024-01-30","cited_by_count":26,"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":"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":"2401.04531","title":"MERA: A Comprehensive LLM Evaluation in Russian","created":"2024-01-09","cited_by_count":22,"area":null},{"id":"2109.00227","title":"Dataset for Identification of Homophobia and Transophobia in Multilingual YouTube Comments","created":"2021-09-01","cited_by_count":20,"area":null},{"id":"2402.04513","title":"Online Cascade Learning for Efficient Inference over Streams","created":"2024-02-07","cited_by_count":20,"area":null},{"id":"2406.07457","title":"Estimating the Hallucination Rate of Generative AI","created":"2024-06-11","cited_by_count":20,"area":null},{"id":"2109.13137","title":"Mitigating Racial Biases in Toxic Language Detection with an Equity-Based Ensemble Framework","created":"2021-09-27","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":"2206.15455","title":"Hate Speech Criteria: A Modular Approach to Task-Specific Hate Speech Definitions","created":"2022-06-30","cited_by_count":18,"area":null},{"id":"2206.04007","title":"Proactively Reducing the Hate Intensity of Online Posts via Hate Speech Normalization","created":"2022-06-08","cited_by_count":17,"area":null},{"id":"2205.00328","title":"HateCheckHIn: Evaluating Hindi Hate Speech Detection Models","created":"2022-04-30","cited_by_count":15,"area":null},{"id":"2106.06213","title":"CONDA: a CONtextual Dual-Annotated dataset for in-game toxicity understanding and detection","created":"2021-06-11","cited_by_count":14,"area":null},{"id":"2205.11315","title":"KOLD: Korean Offensive Language Dataset","created":"2022-05-23","cited_by_count":14,"area":null},{"id":"2205.14036","title":"StereoKG: Data-Driven Knowledge Graph Construction for Cultural Knowledge and Stereotypes","created":"2022-05-27","cited_by_count":14,"area":null},{"id":"2206.00372","title":"BD-SHS: A Benchmark Dataset for Learning to Detect Online Bangla Hate Speech in Different Social Contexts","created":"2022-06-01","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":"2109.00591","title":"Fight Fire with Fire: Fine-tuning Hate Detectors using Large Samples of Generated Hate Speech","created":"2021-09-01","cited_by_count":13,"area":null},{"id":"2409.07132","title":"LLM-based feature generation from text for interpretable machine learning","created":"2024-09-11","cited_by_count":13,"area":null},{"id":"2508.09093","title":"Scaling Up Active Testing to Large Language Models","created":"2025-08-12","cited_by_count":13,"area":null},{"id":"2411.05214","title":"STAND-Guard: A Small Task-Adaptive Content Moderation Model","created":"2024-11-07","cited_by_count":12,"area":null},{"id":"2108.00524","title":"You too Brutus! Trapping Hateful Users in Social Media: Challenges, Solutions & Insights","created":"2021-08-01","cited_by_count":11,"area":null},{"id":"2202.07991","title":"ADIMA: Abuse Detection In Multilingual Audio","created":"2022-02-16","cited_by_count":11,"area":null},{"id":"2204.09347","title":"Active Few-Shot Learning with FASL","created":"2022-04-20","cited_by_count":11,"area":null},{"id":"2302.08143","title":"Learning to Initialize: Can Meta Learning Improve Cross-task Generalization in Prompt Tuning?","created":"2023-02-16","cited_by_count":11,"area":null},{"id":"2405.14660","title":"Implicit In-context Learning","created":"2024-05-23","cited_by_count":11,"area":null},{"id":"2108.01721","title":"Improving Counterfactual Generation for Fair Hate Speech Detection","created":"2021-08-03","cited_by_count":10,"area":null},{"id":"2208.10598","title":"Generalizing Hate Speech Detection Using Multi-Task Learning: A Case Study of Political Public Figures","created":"2022-08-22","cited_by_count":10,"area":null},{"id":"2302.02169","title":"How Many and Which Training Points Would Need to be Removed to Flip this Prediction?","created":"2023-02-04","cited_by_count":10,"area":null},{"id":"2402.15951","title":"DetoxLLM: A Framework for Detoxification with Explanations","created":"2024-02-25","cited_by_count":10,"area":null},{"id":"2106.09775","title":"An Information Retrieval Approach to Building Datasets for Hate Speech Detection","created":"2021-06-17","cited_by_count":9,"area":null},{"id":"2203.16775","title":"Bangla hate speech detection on social media using attention-based recurrent neural network","created":"2022-03-31","cited_by_count":9,"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":"2403.09488","title":"Rectifying Demonstration Shortcut in In-Context Learning","created":"2024-03-14","cited_by_count":9,"area":null},{"id":"2406.16535","title":"Token-based Decision Criteria Are Suboptimal in In-context Learning","created":"2024-06-24","cited_by_count":9,"area":null},{"id":"2408.04965","title":"Generalisation First, Memorisation Second? Memorisation Localisation for Natural Language Classification Tasks","created":"2024-08-09","cited_by_count":9,"area":null},{"id":"2501.15438","title":"Cross-Modal Transfer from Memes to Videos: Addressing Data Scarcity in Hateful Video Detection","created":"2025-01-26","cited_by_count":9,"area":null},{"id":"2502.07138","title":"Towards a Robust Framework for Multimodal Hate Detection: A Study on Video vs. Image-based Content","created":"2025-02-11","cited_by_count":9,"area":null},{"id":"2210.16978","title":"XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models","created":"2022-10-30","cited_by_count":8,"area":null},{"id":"2211.02882","title":"HERB: Measuring Hierarchical Regional Bias in Pre-trained Language Models","created":"2022-11-05","cited_by_count":8,"area":null},{"id":"2308.08780","title":"Exploring Demonstration Ensembling for In-context Learning","created":"2023-08-17","cited_by_count":8,"area":null},{"id":"2111.06336","title":"Character-level HyperNetworks for Hate Speech Detection","created":"2021-11-11","cited_by_count":7,"area":null},{"id":"2203.14349","title":"Reinforcement Guided Multi-Task Learning Framework for Low-Resource Stereotype Detection","created":"2022-03-27","cited_by_count":7,"area":null},{"id":"2306.01105","title":"Revisiting Hate Speech Benchmarks: From Data Curation to System Deployment","created":"2023-06-01","cited_by_count":7,"area":null},{"id":"2311.09993","title":"Generative AI for Hate Speech Detection: Evaluation and Findings","created":"2023-11-16","cited_by_count":7,"area":null},{"id":"2107.12866","title":"Unsupervised Domain Adaptation for Hate Speech Detection Using a Data Augmentation Approach","created":"2021-07-27","cited_by_count":6,"area":null},{"id":"2205.01374","title":"Hidden behind the obvious: misleading keywords and implicitly abusive language on social media","created":"2022-05-03","cited_by_count":6,"area":null},{"id":"2205.12542","title":"ER-Test: Evaluating Explanation Regularization Methods for Language Models","created":"2022-05-25","cited_by_count":6,"area":null},{"id":"2208.01009","title":"Few-shot Adaptation Works with UnpredicTable Data","created":"2022-08-01","cited_by_count":6,"area":null},{"id":"2305.13276","title":"Evaluating ChatGPT's Performance for Multilingual and Emoji-based Hate Speech Detection","created":"2023-05-22","cited_by_count":6,"area":null},{"id":"2310.14047","title":"MeaeQ: Mount Model Extraction Attacks with Efficient Queries","created":"2023-10-21","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":"2407.17011","title":"Unveiling In-Context Learning: A Coordinate System to Understand Its Working Mechanism","created":"2024-07-24","cited_by_count":6,"area":null},{"id":"2105.11119","title":"Abusive Language Detection in Heterogeneous Contexts: Dataset Collection and the Role of Supervised Attention","created":"2021-05-24","cited_by_count":5,"area":null},{"id":"2301.11579","title":"Down the Rabbit Hole: Detecting Online Extremism, Radicalisation, and Politicised Hate Speech","created":"2023-01-27","cited_by_count":5,"area":null},{"id":"2305.03518","title":"Black-box Prompt Tuning with Subspace Learning","created":"2023-05-04","cited_by_count":5,"area":null},{"id":"2312.17055","title":"Beyond Output Matching: Bidirectional Alignment for Enhanced In-Context Learning","created":"2023-12-28","cited_by_count":5,"area":null},{"id":"2402.01697","title":"APT-Pipe: A Prompt-Tuning Tool for Social Data Annotation using ChatGPT","created":"2024-01-24","cited_by_count":5,"area":null},{"id":"2407.10995","title":"LionGuard: Building a Contextualized Moderation Classifier to Tackle Localized Unsafe Content","created":"2024-06-24","cited_by_count":5,"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":"2508.20546","title":"MM-HSD: Multi-Modal Hate Speech Detection in Videos","created":"2025-08-28","cited_by_count":5,"area":null},{"id":"2102.04895","title":"Leveraging cross-platform data to improve automated hate speech detection","created":"2021-02-09","cited_by_count":4,"area":null},{"id":"2203.03541","title":"Fairness for Text Classification Tasks with Identity Information Data Augmentation Methods","created":"2022-02-04","cited_by_count":4,"area":null},{"id":"2312.04601","title":"Weak Supervision Performance Evaluation via Partial Identification","created":"2023-12-07","cited_by_count":4,"area":null},{"id":"2312.11344","title":"Muted: Multilingual Targeted Offensive Speech Identification and Visualization","created":"2023-12-18","cited_by_count":4,"area":null},{"id":"2401.03385","title":"Grimoire is All You Need for Enhancing Large Language Models","created":"2024-01-07","cited_by_count":4,"area":null},{"id":"2402.05515","title":"NoisyICL: A Little Noise in Model Parameters Calibrates In-context Learning","created":"2024-02-08","cited_by_count":4,"area":null},{"id":"2408.10608","title":"BTBR: A Bayesian-Theory-Driven Probabilistic-Fuzzy Framework for Implicit Bias Removal in Large Language Models","created":"2024-08-20","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":"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}],"next_cursor":"100"}