{"total":374,"rows":[{"id":"2110.15943","title":"MetaICL: Learning to Learn In Context","created":"2021-10-29","cited_by_count":454,"area":null},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2305.08283","title":"From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models","created":"2023-05-15","cited_by_count":260,"area":null},{"id":"2110.01167","title":"Trustworthy AI: From Principles to Practices","created":"2021-10-04","cited_by_count":207,"area":null},{"id":"2203.06904","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","created":"2022-03-14","cited_by_count":180,"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":"2102.12060","title":"Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing","created":"2021-02-24","cited_by_count":126,"area":null},{"id":"2308.10149","title":"A Survey on Fairness in Large Language Models","created":"2023-08-20","cited_by_count":95,"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":"2203.13928","title":"On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations","created":"2022-03-25","cited_by_count":75,"area":null},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"id":"2307.16883","title":"HAGRID: A Human-LLM Collaborative Dataset for Generative Information-Seeking with Attribution","created":"2023-07-31","cited_by_count":56,"area":null},{"id":"2310.12860","title":"Probing LLMs for hate speech detection: strengths and vulnerabilities","created":"2023-10-19","cited_by_count":52,"area":null},{"id":"2206.09917","title":"Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models","created":"2022-06-20","cited_by_count":51,"area":null},{"id":"2210.02938","title":"Debiasing isn't enough! -- On the Effectiveness of Debiasing MLMs and their Social Biases in Downstream Tasks","created":"2022-10-06","cited_by_count":48,"area":null},{"id":"2210.08604","title":"NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly","created":"2022-10-16","cited_by_count":48,"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":"2305.04446","title":"Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks","created":"2023-05-08","cited_by_count":46,"area":null},{"id":"2305.17680","title":"Evaluating GPT-3 Generated Explanations for Hateful Content Moderation","created":"2023-05-28","cited_by_count":46,"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":"2504.00125","title":"LLMs for Explainable AI: A Comprehensive Survey","created":"2025-03-31","cited_by_count":45,"area":null},{"id":"2205.03286","title":"GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers","created":"2022-05-06","cited_by_count":44,"area":null},{"id":"2203.01111","title":"Large-Scale Hate Speech Detection with Cross-Domain Transfer","created":"2022-03-02","cited_by_count":41,"area":null},{"id":"2211.03433","title":"Human-Machine Collaboration Approaches to Build a Dialogue Dataset for Hate Speech Countering","created":"2022-11-07","cited_by_count":40,"area":null},{"id":"2108.01250","title":"Your fairness may vary: Pretrained language model fairness in toxic text classification","created":"2021-08-03","cited_by_count":39,"area":null},{"id":"2308.05596","title":"You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content","created":"2023-08-10","cited_by_count":39,"area":null},{"id":"2410.19317","title":"FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMs","created":"2024-10-25","cited_by_count":36,"area":null},{"id":"2104.08808","title":"Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning","created":"2021-04-18","cited_by_count":35,"area":null},{"id":"2205.12390","title":"Toxicity Detection with Generative Prompt-based Inference","created":"2022-05-24","cited_by_count":35,"area":null},{"id":"2206.06423","title":"Hate Speech and Counter Speech Detection: Conversational Context Does Matter","created":"2022-06-13","cited_by_count":32,"area":null},{"id":"2306.02873","title":"DecompX: Explaining Transformers Decisions by Propagating Token Decomposition","created":"2023-06-05","cited_by_count":31,"area":null},{"id":"2311.00321","title":"HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning","created":"2023-11-01","cited_by_count":31,"area":null},{"id":"2204.01440","title":"Using Pre-Trained Language Models for Producing Counter Narratives Against Hate Speech: a Comparative Study","created":"2022-04-04","cited_by_count":30,"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":"2104.08142","title":"Supervising Model Attention with Human Explanations for Robust Natural Language Inference","created":"2021-04-16","cited_by_count":29,"area":null},{"id":"2205.04304","title":"CounterGeDi: A controllable approach to generate polite, detoxified and emotional counterspeech","created":"2022-05-09","cited_by_count":29,"area":null},{"id":"2307.01680","title":"Robust Hate Speech Detection in Social Media: A Cross-Dataset Empirical Evaluation","created":"2023-07-04","cited_by_count":28,"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":"2208.01575","title":"ferret: a Framework for Benchmarking Explainers on Transformers","created":"2022-08-02","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":"2110.07867","title":"Exploring Universal Intrinsic Task Subspace via Prompt Tuning","created":"2021-10-15","cited_by_count":25,"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":"2405.05378","title":"\"They are uncultured\": Unveiling Covert Harms and Social Threats in LLM Generated Conversations","created":"2024-05-08","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":"2309.04344","title":"Zero-Shot Robustification of Zero-Shot Models","created":"2023-09-08","cited_by_count":24,"area":null},{"id":"2204.12543","title":"Data Bootstrapping Approaches to Improve Low Resource Abusive Language Detection for Indic Languages","created":"2022-04-26","cited_by_count":23,"area":null},{"id":"2210.10839","title":"How Hate Speech Varies by Target Identity: A Computational Analysis","created":"2022-10-19","cited_by_count":23,"area":null},{"id":"2203.11764","title":"Listening to Affected Communities to Define Extreme Speech: Dataset and Experiments","created":"2022-03-22","cited_by_count":22,"area":null},{"id":"2302.05706","title":"MTTM: Metamorphic Testing for Textual Content Moderation Software","created":"2023-02-11","cited_by_count":22,"area":null},{"id":"2312.17543","title":"Building Efficient Universal Classifiers with Natural Language Inference","created":"2023-12-29","cited_by_count":22,"area":null},{"id":"2210.04675","title":"A Survey of Methods for Addressing Class Imbalance in Deep-Learning Based Natural Language Processing","created":"2022-10-10","cited_by_count":21,"area":null},{"id":"2210.13513","title":"ExPUNations: Augmenting Puns with Keywords and Explanations","created":"2022-10-24","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":"2401.03346","title":"An Investigation of Large Language Models for Real-World Hate Speech Detection","created":"2024-01-07","cited_by_count":20,"area":null},{"id":"2203.08991","title":"AdapLeR: Speeding up Inference by Adaptive Length Reduction","created":"2022-03-16","cited_by_count":19,"area":null},{"id":"2210.03479","title":"Hate Speech and Offensive Language Detection in Bengali","created":"2022-10-07","cited_by_count":19,"area":null},{"id":"2210.04710","title":"Empowering the Fact-checkers! Automatic Identification of Claim Spans on Twitter","created":"2022-10-10","cited_by_count":19,"area":null},{"id":"2210.12696","title":"On the Transformation of Latent Space in Fine-Tuned NLP Models","created":"2022-10-23","cited_by_count":19,"area":null},{"id":"2205.03302","title":"Necessity and Sufficiency for Explaining Text Classifiers: A Case Study in Hate Speech Detection","created":"2022-05-06","cited_by_count":18,"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":"2304.13148","title":"Introducing MBIB -- the first Media Bias Identification Benchmark Task and Dataset Collection","created":"2023-04-25","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":"2403.14938","title":"On Zero-Shot Counterspeech Generation by LLMs","created":"2024-03-22","cited_by_count":17,"area":null},{"id":"2204.13746","title":"CAVES: A Dataset to facilitate Explainable Classification and Summarization of Concerns towards COVID Vaccines","created":"2022-04-28","cited_by_count":16,"area":null},{"id":"2301.12534","title":"Vicarious Offense and Noise Audit of Offensive Speech Classifiers: Unifying Human and Machine Disagreement on What is Offensive","created":"2023-01-29","cited_by_count":16,"area":null},{"id":"2403.12403","title":"Towards Interpretable Hate Speech Detection using Large Language Model-extracted Rationales","created":"2024-03-19","cited_by_count":16,"area":null},{"id":"2204.08892","title":"A survey on improving NLP models with human explanations","created":"2022-04-19","cited_by_count":15,"area":null},{"id":"2205.00328","title":"HateCheckHIn: Evaluating Hindi Hate Speech Detection Models","created":"2022-04-30","cited_by_count":15,"area":null},{"id":"2205.11097","title":"A Fine-grained Interpretability Evaluation Benchmark for Neural NLP","created":"2022-05-23","cited_by_count":15,"area":null},{"id":"2105.14888","title":"An Exploratory Analysis of the Relation Between Offensive Language and Mental Health","created":"2021-05-31","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":"2301.11219","title":"Characterizing the Entities in Harmful Memes: Who is the Hero, the Villain, the Victim?","created":"2023-01-26","cited_by_count":14,"area":null},{"id":"2302.09270","title":"Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements","created":"2023-02-18","cited_by_count":14,"area":null},{"id":"2308.12539","title":"CALM : A Multi-task Benchmark for Comprehensive Assessment of Language Model Bias","created":"2023-08-24","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":"2501.16750","title":"HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns","created":"2025-01-28","cited_by_count":14,"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":"2202.09517","title":"Deep Learning for Hate Speech Detection: A Comparative Study","created":"2022-02-19","cited_by_count":13,"area":null},{"id":"2301.10186","title":"ViHOS: Hate Speech Spans Detection for Vietnamese","created":"2023-01-24","cited_by_count":13,"area":null},{"id":"2401.09899","title":"Meme-ingful Analysis: Enhanced Understanding of Cyberbullying in Memes Through Multimodal Explanations","created":"2024-01-18","cited_by_count":13,"area":null},{"id":"2402.16979","title":"Algorithmic Arbitrariness in Content Moderation","created":"2024-02-26","cited_by_count":13,"area":null},{"id":"2408.14141","title":"Crowd-Calibrator: Can Annotator Disagreement Inform Calibration in Subjective Tasks?","created":"2024-08-26","cited_by_count":13,"area":null},{"id":"2411.15462","title":"HateDay: Insights from a Global Hate Speech Dataset Representative of a Day on Twitter","created":"2024-11-23","cited_by_count":13,"area":null},{"id":"2503.01623","title":"Lost in Moderation: How Commercial Content Moderation APIs Over- and Under-Moderate Group-Targeted Hate Speech and Linguistic Variations","created":"2025-03-03","cited_by_count":13,"area":null},{"id":"2505.17510","title":"Large Language Models Do Multi-Label Classification Differently","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2109.02941","title":"Countering Online Hate Speech: An NLP Perspective","created":"2021-09-07","cited_by_count":12,"area":null},{"id":"2303.03387","title":"CoSyn: Detecting Implicit Hate Speech in Online Conversations Using a Context Synergized Hyperbolic Network","created":"2023-03-02","cited_by_count":12,"area":null},{"id":"2306.00639","title":"Being Right for Whose Right Reasons?","created":"2023-06-01","cited_by_count":12,"area":null},{"id":"2308.07902","title":"Through the Lens of Core Competency: Survey on Evaluation of Large Language Models","created":"2023-08-15","cited_by_count":12,"area":null},{"id":"2310.10191","title":"VIBE: Topic-Driven Temporal Adaptation for Twitter Classification","created":"2023-10-16","cited_by_count":12,"area":null},{"id":"2312.01648","title":"Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation","created":"2023-12-04","cited_by_count":12,"area":null},{"id":"2312.16148","title":"The Media Bias Taxonomy: A Systematic Literature Review on the Forms and Automated Detection of Media Bias","created":"2023-12-26","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":"2112.03529","title":"Ground-Truth, Whose Truth? -- Examining the Challenges with Annotating Toxic Text Datasets","created":"2021-12-07","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":"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":"2310.05592","title":"InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations","created":"2023-10-09","cited_by_count":11,"area":null},{"id":"2406.03953","title":"Tox-BART: Leveraging Toxicity Attributes for Explanation Generation of Implicit Hate Speech","created":"2024-06-06","cited_by_count":11,"area":null},{"id":"2502.00837","title":"Explainability in Practice: A Survey of Explainable NLP Across Various Domains","created":"2025-02-02","cited_by_count":11,"area":null},{"id":"2504.06667","title":"Toward Holistic Evaluation of Recommender Systems Powered by Generative Models","created":"2025-04-09","cited_by_count":11,"area":null}],"next_cursor":"100"}