{"total":78,"rows":[{"id":"2308.01263","title":"XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models","created":"2023-08-02","cited_by_count":505,"area":null},{"id":"2112.14168","title":"A Survey on Gender Bias in Natural Language Processing","created":"2021-12-28","cited_by_count":89,"area":null},{"id":"2108.03362","title":"On Measures of Biases and Harms in NLP","created":"2021-08-07","cited_by_count":81,"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":"2203.09192","title":"Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists","created":"2022-03-17","cited_by_count":55,"area":null},{"id":"2302.02463","title":"Nationality Bias in Text Generation","created":"2023-02-05","cited_by_count":50,"area":null},{"id":"2303.04222","title":"SemEval-2023 Task 10: Explainable Detection of Online Sexism","created":"2023-03-07","cited_by_count":48,"area":null},{"id":"2305.03915","title":"HateMM: A Multi-Modal Dataset for Hate Video Classification","created":"2023-05-06","cited_by_count":42,"area":null},{"id":"2204.01734","title":"On Explaining Multimodal Hateful Meme Detection Models","created":"2022-04-04","cited_by_count":29,"area":null},{"id":"2306.08158","title":"Sociodemographic Bias in Language Models: A Survey and Forward Path","created":"2023-06-13","cited_by_count":28,"area":null},{"id":"2103.10415","title":"Refining Language Models with Compositional Explanations","created":"2021-03-18","cited_by_count":27,"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":"2203.00056","title":"An Empirical Study on Explanations in Out-of-Domain Settings","created":"2022-02-28","cited_by_count":21,"area":null},{"id":"2206.03945","title":"Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models","created":"2022-06-08","cited_by_count":20,"area":null},{"id":"2109.10444","title":"Fairness-aware Class Imbalanced Learning","created":"2021-09-21","cited_by_count":19,"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":"2110.04419","title":"Detecting Community Sensitive Norm Violations in Online Conversations","created":"2021-10-09","cited_by_count":18,"area":null},{"id":"2108.13759","title":"Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience","created":"2021-08-31","cited_by_count":16,"area":null},{"id":"2308.04346","title":"Unmasking Nationality Bias: A Study of Human Perception of Nationalities in AI-Generated Articles","created":"2023-08-08","cited_by_count":16,"area":null},{"id":"2205.11315","title":"KOLD: Korean Offensive Language Dataset","created":"2022-05-23","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":"2111.13259","title":"Identification of Bias Against People with Disabilities in Sentiment Analysis and Toxicity Detection Models","created":"2021-11-25","cited_by_count":13,"area":null},{"id":"2110.14839","title":"Hate Speech Classifiers Learn Human-Like Social Stereotypes","created":"2021-10-28","cited_by_count":12,"area":null},{"id":"2205.04238","title":"Counterfactually Augmented Data and Unintended Bias: The Case of Sexism and Hate Speech Detection","created":"2022-05-09","cited_by_count":11,"area":null},{"id":"2210.02659","title":"Explainable Abuse Detection as Intent Classification and Slot Filling","created":"2022-10-06","cited_by_count":11,"area":null},{"id":"2305.13088","title":"Should We Attend More or Less? Modulating Attention for Fairness","created":"2023-05-22","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":"2210.13029","title":"Multilingual Auxiliary Tasks Training: Bridging the Gap between Languages for Zero-Shot Transfer of Hate Speech Detection Models","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2405.20628","title":"ToxVidLM: A Multimodal Framework for Toxicity Detection in Code-Mixed Videos","created":"2024-05-31","cited_by_count":10,"area":null},{"id":"2106.05903","title":"Deciphering Implicit Hate: Evaluating Automated Detection Algorithms for Multimodal Hate","created":"2021-06-10","cited_by_count":8,"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":"2111.06336","title":"Character-level HyperNetworks for Hate Speech Detection","created":"2021-11-11","cited_by_count":7,"area":null},{"id":"2210.11359","title":"Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages","created":"2022-10-20","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":"2403.16685","title":"ToXCL: A Unified Framework for Toxic Speech Detection and Explanation","created":"2024-03-25","cited_by_count":7,"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":"2205.12542","title":"ER-Test: Evaluating Explanation Regularization Methods for Language Models","created":"2022-05-25","cited_by_count":6,"area":null},{"id":"2210.06725","title":"Assessing Out-of-Domain Language Model Performance from Few Examples","created":"2022-10-13","cited_by_count":6,"area":null},{"id":"2210.10689","title":"Towards Procedural Fairness: Uncovering Biases in How a Toxic Language Classifier Uses Sentiment Information","created":"2022-10-19","cited_by_count":6,"area":null},{"id":"2209.09975","title":"Power of Explanations: Towards automatic debiasing in hate speech detection","created":"2022-09-07","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":"2110.05301","title":"On a Benefit of Mask Language Modeling: Robustness to Simplicity Bias","created":"2021-10-11","cited_by_count":4,"area":null},{"id":"2310.14418","title":"REFER: An End-to-end Rationale Extraction Framework for Explanation Regularization","created":"2023-10-22","cited_by_count":4,"area":null},{"id":"2404.12042","title":"Exploring Boundaries and Intensities in Offensive and Hate Speech: Unveiling the Complex Spectrum of Social Media Discourse","created":"2024-04-18","cited_by_count":4,"area":null},{"id":"2203.12536","title":"Dynamically Refined Regularization for Improving Cross-corpora Hate Speech Detection","created":"2022-03-23","cited_by_count":3,"area":null},{"id":"2206.08445","title":"Enriching Abusive Language Detection with Community Context","created":"2022-06-16","cited_by_count":3,"area":null},{"id":"2305.10731","title":"Analyzing Norm Violations in Live-Stream Chat","created":"2023-05-18","cited_by_count":3,"area":null},{"id":"2309.01413","title":"Hateful Messages: A Conversational Data Set of Hate Speech produced by Adolescents on Discord","created":"2023-09-04","cited_by_count":3,"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":"2109.02691","title":"SS-BERT: Mitigating Identity Terms Bias in Toxic Comment Classification by Utilising the Notion of \"Subjectivity\" and \"Identity Terms\"","created":"2021-09-06","cited_by_count":2,"area":null},{"id":"2112.07327","title":"Model Uncertainty-Aware Knowledge Amalgamation for Pre-Trained Language Models","created":"2021-12-14","cited_by_count":2,"area":null},{"id":"2210.12233","title":"TCAB: A Large-Scale Text Classification Attack Benchmark","created":"2022-10-21","cited_by_count":2,"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":"2309.16905","title":"Towards a Unified Framework for Adaptable Problematic Content Detection via Continual Learning","created":"2023-09-29","cited_by_count":2,"area":null},{"id":"2311.09834","title":"Overview of the HASOC Subtrack at FIRE 2023: Identification of Tokens Contributing to Explicit Hate in English by Span Detection","created":"2023-11-16","cited_by_count":2,"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":"2505.00802","title":"Explanations as Bias Detectors: A Critical Study of Local Post-hoc XAI Methods for Fairness Exploration","created":"2025-05-01","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":"2505.24538","title":"Don't Erase, Inform! Detecting and Contextualizing Harmful Language in Cultural Heritage Collections","created":"2025-05-30","cited_by_count":2,"area":null},{"id":"2110.08536","title":"Sparse Distillation: Speeding Up Text Classification by Using Bigger Student Models","created":"2021-10-16","cited_by_count":1,"area":null},{"id":"2201.11770","title":"Going Extreme: Comparative Analysis of Hate Speech in Parler and Gab","created":"2022-01-27","cited_by_count":1,"area":null},{"id":"2203.07640","title":"Unsupervised Keyphrase Extraction via Interpretable Neural Networks","created":"2022-03-15","cited_by_count":1,"area":null},{"id":"2210.05230","title":"From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models","created":"2022-10-11","cited_by_count":1,"area":null},{"id":"2301.10368","title":"Language Model Detoxification in Dialogue with Contextualized Stance Control","created":"2023-01-25","cited_by_count":1,"area":null},{"id":"2302.07733","title":"Explaining text classifiers through progressive neighborhood approximation with realistic samples","created":"2023-02-11","cited_by_count":1,"area":null},{"id":"2306.03722","title":"Evaluating the Effectiveness of Natural Language Inference for Hate Speech Detection in Languages with Limited Labeled Data","created":"2023-06-06","cited_by_count":1,"area":null},{"id":"2407.11933","title":"Fairness-Aware Multi-Group Target Detection in Online Discussion","created":"2024-07-16","cited_by_count":1,"area":null},{"id":"2506.03916","title":"Compositional Generalisation for Explainable Hate Speech Detection","created":"2025-06-04","cited_by_count":1,"area":null},{"id":"2105.11412","title":"Reproducibility Report: Contextualizing Hate Speech Classifiers with Post-hoc Explanation","created":"2021-05-24","cited_by_count":0,"area":null},{"id":"2209.08681","title":"Domain Classification-based Source-specific Term Penalization for Domain Adaptation in Hate-speech Detection","created":"2022-09-18","cited_by_count":0,"area":null},{"id":"2403.14467","title":"Recourse for reclamation: Chatting with generative language models","created":"2024-03-21","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":"2501.00907","title":"U-GIFT: Uncertainty-Guided Firewall for Toxic Speech in Few-Shot Scenario","created":"2025-01-01","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":"2604.14970","title":"Explain the Flag: Contextualizing Hate Speech Beyond Censorship","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2607.20946","title":"From a Word-Level Dictionary to Sentence-Level Semantics: Multilingual Grievance Labelling with Contextual Models","created":"2026-07-23","cited_by_count":0,"area":null}],"next_cursor":null}