{"total":216,"rows":[{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326,"area":null},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026,"area":"safety"},{"id":"2209.07858","title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","created":"2022-08-23","cited_by_count":729,"area":"alignment"},{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701,"area":null},{"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":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459,"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":"2602.12275","title":"On-Policy Context Distillation for Language Models","created":"2026-02-12","cited_by_count":186,"area":"distill"},{"id":"2302.08500","title":"Auditing large language models: a three-layered approach","created":"2023-02-16","cited_by_count":137,"area":null},{"id":"2401.15897","title":"Red-Teaming for Generative AI: Silver Bullet or Security Theater?","created":"2024-01-29","cited_by_count":83,"area":"safety"},{"id":"2107.03451","title":"Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling","created":"2021-07-07","cited_by_count":78,"area":null},{"id":"2205.00501","title":"Is Your Toxicity My Toxicity? Exploring the Impact of Rater Identity on Toxicity Annotation","created":"2022-05-01","cited_by_count":69,"area":null},{"id":"2106.06052","title":"Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking","created":"2021-05-21","cited_by_count":53,"area":null},{"id":"2205.12586","title":"Perturbation Augmentation for Fairer NLP","created":"2022-05-25","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":"2108.05921","title":"Hatemoji: A Test Suite and Adversarially-Generated Dataset for Benchmarking and Detecting Emoji-based Hate","created":"2021-08-12","cited_by_count":50,"area":null},{"id":"2410.03415","title":"Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation","created":"2024-10-04","cited_by_count":48,"area":null},{"id":"2310.02224","title":"Can Language Models be Instructed to Protect Personal Information?","created":"2023-10-03","cited_by_count":46,"area":"mllm"},{"id":"2507.21206","title":"Agentic Web: Weaving the Next Web with AI Agents","created":"2025-07-28","cited_by_count":45,"area":"agents"},{"id":"2204.14256","title":"Handling and Presenting Harmful Text in NLP Research","created":"2022-04-29","cited_by_count":43,"area":null},{"id":"2210.04337","title":"Quantifying Social Biases Using Templates is Unreliable","created":"2022-10-09","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":"2306.01985","title":"COBRA Frames: Contextual Reasoning about Effects and Harms of Offensive Statements","created":"2023-06-03","cited_by_count":34,"area":null},{"id":"2305.17444","title":"Query-Efficient Black-Box Red Teaming via Bayesian Optimization","created":"2023-05-27","cited_by_count":32,"area":"safety"},{"id":"2310.16524","title":"Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Data","created":"2023-10-25","cited_by_count":32,"area":null},{"id":"2407.12824","title":"Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models","created":"2024-07-02","cited_by_count":32,"area":null},{"id":"2303.18190","title":"Assessing Language Model Deployment with Risk Cards","created":"2023-03-31","cited_by_count":30,"area":null},{"id":"2212.10529","title":"Evaluating Psychological Safety of Large Language Models","created":"2022-12-20","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":"2305.17174","title":"From Dogwhistles to Bullhorns: Unveiling Coded Rhetoric with Language Models","created":"2023-05-26","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":"2311.01270","title":"People Make Better Edits: Measuring the Efficacy of LLM-Generated Counterfactually Augmented Data for Harmful Language Detection","created":"2023-11-02","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":"2305.17701","title":"KoSBi: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Application","created":"2023-05-28","cited_by_count":24,"area":null},{"id":"2105.05996","title":"Multilingual Offensive Language Identification for Low-resource Languages","created":"2021-05-12","cited_by_count":22,"area":null},{"id":"2109.08256","title":"Ethics Sheet for Automatic Emotion Recognition and Sentiment Analysis","created":"2021-09-17","cited_by_count":22,"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":"2403.20103","title":"NLP for Counterspeech against Hate: A Survey and How-To Guide","created":"2024-03-29","cited_by_count":22,"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":"2403.08994","title":"Ethos: Rectifying Language Models in Orthogonal Parameter Space","created":"2024-03-13","cited_by_count":20,"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":"2505.09666","title":"System Prompt Optimization with Meta-Learning","created":"2025-05-14","cited_by_count":18,"area":null},{"id":"2205.00328","title":"HateCheckHIn: Evaluating Hindi Hate Speech Detection Models","created":"2022-04-30","cited_by_count":15,"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":"2502.11073","title":"Demystifying Hateful Content: Leveraging Large Multimodal Models for Hateful Meme Detection with Explainable Decisions","created":"2025-02-16","cited_by_count":14,"area":"mllm"},{"id":"2206.13757","title":"Flexible text generation for counterfactual fairness probing","created":"2022-06-28","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":"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":"2109.10255","title":"Multi-Task Learning with Sentiment, Emotion, and Target Detection to Recognize Hate Speech and Offensive Language","created":"2021-09-21","cited_by_count":12,"area":null},{"id":"2112.07475","title":"Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks","created":"2021-12-14","cited_by_count":12,"area":null},{"id":"2304.05967","title":"Angler: Helping Machine Translation Practitioners Prioritize Model Improvements","created":"2023-04-12","cited_by_count":12,"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":"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":"2502.14019","title":"Dehumanizing Machines: Mitigating Anthropomorphic Behaviors in Text Generation Systems","created":"2025-02-19","cited_by_count":11,"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":"2302.07372","title":"Same Same, But Different: Conditional Multi-Task Learning for Demographic-Specific Toxicity Detection","created":"2023-02-14","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":"2403.19260","title":"NaijaHate: Evaluating Hate Speech Detection on Nigerian Twitter Using Representative Data","created":"2024-03-28","cited_by_count":10,"area":null},{"id":"2405.01842","title":"SGHateCheck: Functional Tests for Detecting Hate Speech in Low-Resource Languages of Singapore","created":"2024-05-03","cited_by_count":10,"area":null},{"id":"2410.03448","title":"\"Cold, Calculated, and Condescending\": How AI Identifies and Explains Ableism Compared to Disabled People","created":"2024-10-04","cited_by_count":10,"area":null},{"id":"2106.09462","title":"pysentimiento: A Python Toolkit for Opinion Mining and Social NLP tasks","created":"2021-06-17","cited_by_count":9,"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":"2203.17090","title":"PanGu-Bot: Efficient Generative Dialogue Pre-training from Pre-trained Language Model","created":"2022-03-31","cited_by_count":9,"area":null},{"id":"2310.09668","title":"Beyond Testers' Biases: Guiding Model Testing with Knowledge Bases using LLMs","created":"2023-10-14","cited_by_count":9,"area":null},{"id":"2506.07524","title":"TAI3: Testing Agent Integrity in Interpreting User Intent","created":"2025-06-09","cited_by_count":9,"area":"agents"},{"id":"2212.01810","title":"Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation","created":"2022-12-04","cited_by_count":8,"area":null},{"id":"2405.05418","title":"Mitigating Exaggerated Safety in Large Language Models","created":"2024-05-08","cited_by_count":8,"area":null},{"id":"2410.24005","title":"Context-Aware Testing: A New Paradigm for Model Testing with Large Language Models","created":"2024-10-31","cited_by_count":8,"area":null},{"id":"2504.19674","title":"SAGE: A Generic Framework for LLM Safety Evaluation","created":"2025-04-28","cited_by_count":8,"area":"safety"},{"id":"2505.12051","title":"Enhanced Multimodal Hate Video Detection via Channel-wise and Modality-wise Fusion","created":"2025-05-17","cited_by_count":8,"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":"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":"2306.00374","title":"CFL: Causally Fair Language Models Through Token-level Attribute Controlled Generation","created":"2023-06-01","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":"2307.02191","title":"Evaluating AI systems under uncertain ground truth: a case study in dermatology","created":"2023-07-05","cited_by_count":7,"area":null},{"id":"2307.12418","title":"HateModerate: Testing Hate Speech Detectors against Content Moderation Policies","created":"2023-07-23","cited_by_count":7,"area":null},{"id":"2308.13768","title":"Adversarial Fine-Tuning of Language Models: An Iterative Optimisation Approach for the Generation and Detection of Problematic Content","created":"2023-08-26","cited_by_count":7,"area":"safety"},{"id":"2402.02113","title":"Zero-shot Sentiment Analysis in Low-Resource Languages Using a Multilingual Sentiment Lexicon","created":"2024-02-03","cited_by_count":7,"area":null},{"id":"2410.15911","title":"DefVerify: Do Hate Speech Models Reflect Their Dataset's Definition?","created":"2024-10-21","cited_by_count":7,"area":null},{"id":"2505.06149","title":"Can Prompting LLMs Unlock Hate Speech Detection across Languages? A Zero-shot and Few-shot Study","created":"2025-05-09","cited_by_count":7,"area":null},{"id":"2506.18576","title":"A Modular Taxonomy for Hate Speech Definitions and Its Impact on Zero-Shot LLM Classification Performance","created":"2025-06-23","cited_by_count":7,"area":"safety"},{"id":"2111.15512","title":"What Do You See in this Patient? Behavioral Testing of Clinical NLP Models","created":"2021-11-30","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":"2301.01874","title":"Critical Perspectives: A Benchmark Revealing Pitfalls in PerspectiveAPI","created":"2023-01-05","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":"2408.17437","title":"SYNTHEVAL: Hybrid Behavioral Testing of NLP Models with Synthetic CheckLists","created":"2024-08-30","cited_by_count":6,"area":null},{"id":"2409.03274","title":"Recent Advances in Attack and Defense Approaches of Large Language Models","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2505.12727","title":"What is Stigma Attributed to? A Theory-Grounded, Expert-Annotated Interview Corpus for Demystifying Mental-Health Stigma","created":"2025-05-19","cited_by_count":6,"area":null},{"id":"2601.03087","title":"Audit Me If You Can: Query-Efficient Active Fairness Auditing of Black-Box LLMs","created":"2026-01-06","cited_by_count":6,"area":null},{"id":"2206.04137","title":"Adversarial Text Normalization","created":"2022-06-08","cited_by_count":5,"area":null},{"id":"2302.10291","title":"Can Large Language Models Change User Preference Adversarially?","created":"2023-01-05","cited_by_count":5,"area":"safety"},{"id":"2305.13623","title":"Validating Multimedia Content Moderation Software via Semantic Fusion","created":"2023-05-23","cited_by_count":5,"area":null},{"id":"2310.15439","title":"K-HATERS: A Hate Speech Detection Corpus in Korean with Target-Specific Ratings","created":"2023-10-24","cited_by_count":5,"area":null},{"id":"2403.11456","title":"HateCOT: An Explanation-Enhanced Dataset for Generalizable Offensive Speech Detection via Large Language Models","created":"2024-03-18","cited_by_count":5,"area":null},{"id":"2501.16235","title":"Echoes of Discord: Forecasting Hater Reactions to Counterspeech","created":"2025-01-27","cited_by_count":5,"area":null}],"next_cursor":"100"}