{"total":221,"rows":[{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799,"area":null},{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701,"area":null},{"id":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686,"area":"lr"},{"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":"2110.05719","title":"Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations","created":"2021-10-12","cited_by_count":314,"area":null},{"id":"2111.07997","title":"Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection","created":"2021-11-15","cited_by_count":264,"area":null},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2305.13169","title":"A Pretrainer's Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicity","created":"2023-05-22","cited_by_count":182,"area":null},{"id":"2110.07574","title":"Can Machines Learn Morality? The Delphi Experiment","created":"2021-10-14","cited_by_count":141,"area":null},{"id":"2306.01943","title":"NLPositionality: Characterizing Design Biases of Datasets and Models","created":"2023-06-02","cited_by_count":94,"area":null},{"id":"2402.19464","title":"Curiosity-driven Red-teaming for Large Language Models","created":"2024-02-29","cited_by_count":88,"area":"safety"},{"id":"2504.08165","title":"Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora","created":"2025-04-10","cited_by_count":88,"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":"2104.08678","title":"Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation","created":"2021-04-18","cited_by_count":79,"area":null},{"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":"2106.02280","title":"Human-Adversarial Visual Question Answering","created":"2021-06-04","cited_by_count":57,"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":"2405.18540","title":"Learning diverse attacks on large language models for robust red-teaming and safety tuning","created":"2024-05-28","cited_by_count":54,"area":"safety"},{"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":"2206.09917","title":"Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models","created":"2022-06-20","cited_by_count":51,"area":null},{"id":"2402.16444","title":"ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors","created":"2024-02-26","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":"2303.04222","title":"SemEval-2023 Task 10: Explainable Detection of Online Sexism","created":"2023-03-07","cited_by_count":48,"area":null},{"id":"2302.00871","title":"Using In-Context Learning to Improve Dialogue Safety","created":"2023-02-02","cited_by_count":42,"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":"2212.10543","title":"Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts","created":"2022-12-20","cited_by_count":36,"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":"2402.13605","title":"KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge","created":"2024-02-21","cited_by_count":33,"area":"alignment"},{"id":"2311.09090","title":"Social Bias Probing: Fairness Benchmarking for Language Models","created":"2023-11-15","cited_by_count":32,"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":"2405.00722","title":"LLMs for Generating and Evaluating Counterfactuals: A Comprehensive Study","created":"2024-04-26","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":"2303.18190","title":"Assessing Language Model Deployment with Risk Cards","created":"2023-03-31","cited_by_count":30,"area":null},{"id":"2104.07179","title":"Does Putting a Linguist in the Loop Improve NLU Data Collection?","created":"2021-04-15","cited_by_count":29,"area":null},{"id":"2503.18929","title":"Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training","created":"2025-03-24","cited_by_count":29,"area":"lr"},{"id":"2212.10529","title":"Evaluating Psychological Safety of Large Language Models","created":"2022-12-20","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":"2412.18693","title":"Diverse and Effective Red Teaming with Auto-generated Rewards and Multi-step Reinforcement Learning","created":"2024-12-24","cited_by_count":25,"area":"safety"},{"id":"2311.09799","title":"How Far Can We Extract Diverse Perspectives from Large Language Models?","created":"2023-11-16","cited_by_count":22,"area":null},{"id":"2312.08303","title":"Efficient Toxic Content Detection by Bootstrapping and Distilling Large Language Models","created":"2023-12-13","cited_by_count":21,"area":"synth"},{"id":"2410.11745","title":"Personas with Attitudes: Controlling LLMs for Diverse Data Annotation","created":"2024-10-15","cited_by_count":21,"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":"2404.01651","title":"NLP Systems That Can't Tell Use from Mention Censor Counterspeech, but Teaching the Distinction Helps","created":"2024-04-02","cited_by_count":20,"area":null},{"id":"2406.15567","title":"SAIL: Self-Improving Efficient Online Alignment of Large Language Models","created":"2024-06-21","cited_by_count":20,"area":"alignment"},{"id":"2410.01524","title":"HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models","created":"2024-10-02","cited_by_count":19,"area":"distill"},{"id":"2312.15099","title":"Moderating New Waves of Online Hate with Chain-of-Thought Reasoning in Large Language Models","created":"2023-12-22","cited_by_count":18,"area":"lr"},{"id":"2403.03893","title":"From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models","created":"2024-03-06","cited_by_count":18,"area":null},{"id":"2406.14230","title":"Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing","created":"2024-06-20","cited_by_count":17,"area":null},{"id":"2407.15366","title":"Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias","created":"2024-07-22","cited_by_count":17,"area":null},{"id":"2204.01906","title":"Dynatask: A Framework for Creating Dynamic AI Benchmark Tasks","created":"2022-04-05","cited_by_count":16,"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":"2210.12687","title":"BotsTalk: Machine-sourced Framework for Automatic Curation of Large-scale Multi-skill Dialogue Datasets","created":"2022-10-23","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":"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":"2405.06996","title":"Quite Good, but Not Enough: Nationality Bias in Large Language Models -- A Case Study of ChatGPT","created":"2024-05-11","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":"2410.16638","title":"LLMScan: Causal Scan for LLM Misbehavior Detection","created":"2024-10-22","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":"2112.07475","title":"Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks","created":"2021-12-14","cited_by_count":12,"area":null},{"id":"2212.10405","title":"AnnoBERT: Effectively Representing Multiple Annotators' Label Choices to Improve Hate Speech Detection","created":"2022-12-20","cited_by_count":12,"area":null},{"id":"2409.12958","title":"MURI: High-Quality Instruction Tuning Datasets for Low-Resource Languages via Reverse Instructions","created":"2024-09-19","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":"2501.08284","title":"AfriHate: A Multilingual Collection of Hate Speech and Abusive Language Datasets for African Languages","created":"2025-01-14","cited_by_count":11,"area":null},{"id":"2505.19281","title":"A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning","created":"2025-05-25","cited_by_count":11,"area":"deeprl"},{"id":"2409.00787","title":"The Dark Side of Human Feedback: Poisoning Large Language Models via User Inputs","created":"2024-09-01","cited_by_count":10,"area":"alignment"},{"id":"2403.02268","title":"Subjective $\\textit{Isms}$? On the Danger of Conflating Hate and Offence in Abusive Language Detection","created":"2024-03-04","cited_by_count":9,"area":null},{"id":"2408.12494","title":"GenderCARE: A Comprehensive Framework for Assessing and Reducing Gender Bias in Large Language Models","created":"2024-08-22","cited_by_count":9,"area":null},{"id":"2410.01106","title":"Statistical inference on black-box generative models in the data kernel perspective space","created":"2024-10-01","cited_by_count":9,"area":null},{"id":"2410.19406","title":"An Auditing Test To Detect Behavioral Shift in Language Models","created":"2024-10-25","cited_by_count":9,"area":null},{"id":"2501.01558","title":"Predicting the Performance of Black-box LLMs through Follow-up Queries","created":"2025-01-02","cited_by_count":9,"area":null},{"id":"2505.24842","title":"Cascading Adversarial Bias from Injection to Distillation in Language Models","created":"2025-05-30","cited_by_count":9,"area":null},{"id":"2206.14729","title":"longhorns at DADC 2022: How many linguists does it take to fool a Question Answering model? A systematic approach to adversarial attacks","created":"2022-06-29","cited_by_count":8,"area":null},{"id":"2403.19836","title":"Target Span Detection for Implicit Harmful Content","created":"2024-03-28","cited_by_count":8,"area":"safety"},{"id":"2504.20500","title":"UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation","created":"2025-04-29","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":"2305.14384","title":"Adversarial Nibbler: A Data-Centric Challenge for Improving the Safety of Text-to-Image Models","created":"2023-05-22","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":"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":"2402.03221","title":"\"Define Your Terms\" : Enhancing Efficient Offensive Speech Classification with Definition","created":"2024-02-05","cited_by_count":7,"area":null},{"id":"2405.01577","title":"HateTinyLLM : Hate Speech Detection Using Tiny Large Language Models","created":"2024-04-26","cited_by_count":7,"area":null},{"id":"2406.04106","title":"Explainability and Hate Speech: Structured Explanations Make Social Media Moderators Faster","created":"2024-06-06","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":"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":"2301.01874","title":"Critical Perspectives: A Benchmark Revealing Pitfalls in PerspectiveAPI","created":"2023-01-05","cited_by_count":6,"area":null},{"id":"2307.09312","title":"Multi-Modal Discussion Transformer: Integrating Text, Images and Graph Transformers to Detect Hate Speech on Social Media","created":"2023-07-18","cited_by_count":6,"area":null},{"id":"2405.12604","title":"Tiny Refinements Elicit Resilience: Toward Efficient Prefix-Model Against LLM Red-Teaming","created":"2024-05-21","cited_by_count":6,"area":"safety"},{"id":"2406.10882","title":"SCAR: Data Selection via Style Consistency-Aware Response Ranking for Efficient Instruction-Tuning of Large Language Models","created":"2024-06-16","cited_by_count":6,"area":null},{"id":"2410.00775","title":"Decoding Hate: Exploring Language Models' Reactions to Hate Speech","created":"2024-10-01","cited_by_count":6,"area":null},{"id":"2412.12072","title":"Making FETCH! Happen: Finding Emergent Dog Whistles Through Common Habitats","created":"2024-12-16","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":"2506.10403","title":"Time To Impeach LLM-as-a-Judge: Programs are the Future of Evaluation","created":"2025-06-12","cited_by_count":6,"area":null},{"id":"2206.04137","title":"Adversarial Text Normalization","created":"2022-06-08","cited_by_count":5,"area":null}],"next_cursor":"100"}