{"list":"other","total":75,"rows":[{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"2005.14050","title":"Language (Technology) is Power: A Critical Survey of \"Bias\" in NLP","created":"2020-05-28","cited_by_count":956},{"id":"1912.02164","title":"Plug and Play Language Models: A Simple Approach to Controlled Text Generation","created":"2019-12-04","cited_by_count":799},{"id":"1703.04009","title":"Automated Hate Speech Detection and the Problem of Offensive Language","created":"2017-03-11","cited_by_count":736},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"2105.03023","title":"DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts","created":"2021-05-07","cited_by_count":441},{"id":"2012.10289","title":"HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection","created":"2020-12-18","cited_by_count":407},{"id":"1903.04561","title":"Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification","created":"2019-03-11","cited_by_count":404},{"id":"1912.05511","title":"Measurement and Fairness","created":"2019-12-11","cited_by_count":308},{"id":"2111.07997","title":"Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection","created":"2021-11-15","cited_by_count":264},{"id":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247},{"id":"2310.17389","title":"ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation","created":"2023-10-26","cited_by_count":231},{"id":"2012.15606","title":"HateCheck: Functional Tests for Hate Speech Detection Models","created":"2020-12-31","cited_by_count":216},{"id":"1610.08914","title":"Ex Machina: Personal Attacks Seen at Scale","created":"2016-10-27","cited_by_count":210},{"id":"2202.11176","title":"A New Generation of Perspective API: Efficient Multilingual Character-level Transformers","created":"2022-02-22","cited_by_count":185},{"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},{"id":"2004.01670","title":"Directions in Abusive Language Training Data: Garbage In, Garbage Out","created":"2020-04-03","cited_by_count":140},{"id":"1910.03270","title":"CONAN -- COunter NArratives through Nichesourcing: a Multilingual Dataset of Responses to Fight Online Hate Speech","created":"2019-10-08","cited_by_count":110},{"id":"1701.08118","title":"Measuring the Reliability of Hate Speech Annotations: The Case of the European Refugee Crisis","created":"2017-01-27","cited_by_count":96},{"id":"1805.05345","title":"Conversations Gone Awry: Detecting Early Signs of Conversational Failure","created":"2018-05-14","cited_by_count":73},{"id":"2109.13563","title":"Agreeing to Disagree: Annotating Offensive Language Datasets with Annotators' Disagreement","created":"2021-09-28","cited_by_count":72},{"id":"2305.12798","title":"Word Embeddings Are Steers for Language Models","created":"2023-05-22","cited_by_count":70},{"id":"2006.08328","title":"ETHOS: an Online Hate Speech Detection Dataset","created":"2020-06-11","cited_by_count":66},{"id":"2203.13299","title":"Mix and Match: Learning-free Controllable Text Generation using Energy Language Models","created":"2022-03-24","cited_by_count":66},{"id":"2502.00561","title":"Position: Evaluating Generative AI Systems Is a Social Science Measurement Challenge","created":"2025-02-01","cited_by_count":63},{"id":"2202.00126","title":"Handling Bias in Toxic Speech Detection: A Survey","created":"2022-01-26","cited_by_count":61},{"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},{"id":"2303.04222","title":"SemEval-2023 Task 10: Explainable Detection of Online Sexism","created":"2023-03-07","cited_by_count":48},{"id":"2010.04543","title":"Toxic Language Detection in Social Media for Brazilian Portuguese: New Dataset and Multilingual Analysis","created":"2020-10-09","cited_by_count":45},{"id":"2304.12397","title":"On the Challenges of Using Black-Box APIs for Toxicity Evaluation in Research","created":"2023-04-24","cited_by_count":44},{"id":"2203.01111","title":"Large-Scale Hate Speech Detection with Cross-Domain Transfer","created":"2022-03-02","cited_by_count":41},{"id":"2108.07790","title":"Mitigating harm in language models with conditional-likelihood filtration","created":"2021-08-04","cited_by_count":40},{"id":"2206.06423","title":"Hate Speech and Counter Speech Detection: Conversational Context Does Matter","created":"2022-06-13","cited_by_count":32},{"id":"2104.06999","title":"Detecting Cross-Geographic Biases in Toxicity Modeling on Social Media","created":"2021-04-14","cited_by_count":31},{"id":"2305.17174","title":"From Dogwhistles to Bullhorns: Unveiling Coded Rhetoric with Language Models","created":"2023-05-26","cited_by_count":26},{"id":"2404.17874","title":"From Languages to Geographies: Towards Evaluating Cultural Bias in Hate Speech Datasets","created":"2024-04-27","cited_by_count":25},{"id":"2210.10839","title":"How Hate Speech Varies by Target Identity: A Computational Analysis","created":"2022-10-19","cited_by_count":23},{"id":"2105.11596","title":"The Structure of Toxic Conversations on Twitter","created":"2021-05-25","cited_by_count":22},{"id":"2203.11764","title":"Listening to Affected Communities to Define Extreme Speech: Dataset and Experiments","created":"2022-03-22","cited_by_count":22},{"id":"2312.12651","title":"Toxic Bias: Perspective API Misreads German as More Toxic","created":"2023-12-19","cited_by_count":21},{"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},{"id":"2402.11218","title":"Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs","created":"2024-02-17","cited_by_count":16},{"id":"2205.00328","title":"HateCheckHIn: Evaluating Hindi Hate Speech Detection Models","created":"2022-04-30","cited_by_count":15},{"id":"2404.03820","title":"CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues","created":"2024-04-04","cited_by_count":15},{"id":"2304.05274","title":"YouNICon: YouTube's CommuNIty of Conspiracy Videos","created":"2023-04-11","cited_by_count":13},{"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},{"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},{"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},{"id":"2412.11691","title":"Multilingual and Explainable Text Detoxification with Parallel Corpora","created":"2024-12-16","cited_by_count":12},{"id":"2406.03953","title":"Tox-BART: Leveraging Toxicity Attributes for Explanation Generation of Implicit Hate Speech","created":"2024-06-06","cited_by_count":11},{"id":"2410.19109","title":"RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework","created":"2024-10-24","cited_by_count":11},{"id":"2502.11244","title":"Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment","created":"2025-02-16","cited_by_count":10},{"id":"2409.07641","title":"SimulBench: Evaluating Language Models with Creative Simulation Tasks","created":"2024-09-11","cited_by_count":8},{"id":"2305.14307","title":"Debiasing should be Good and Bad: Measuring the Consistency of Debiasing Techniques in Language Models","created":"2023-05-23","cited_by_count":7},{"id":"2403.07904","title":"Addressing the regulatory gap: moving towards an EU AI audit ecosystem beyond the AI Act by including civil society","created":"2024-02-26","cited_by_count":7},{"id":"2506.06404","title":"Unintended Harms of Value-Aligned LLMs: Psychological and Empirical Insights","created":"2025-06-06","cited_by_count":7},{"id":"2005.04412","title":"Characterizing Twitter Users Who Engage in Adversarial Interactions against Political Candidates","created":"2020-05-09","cited_by_count":6},{"id":"2204.12709","title":"Toxicity in the Decentralized Web and the Potential for Model Sharing","created":"2022-04-27","cited_by_count":6},{"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},{"id":"2502.01241","title":"Peering Behind the Shield: Guardrail Identification in Large Language Models","created":"2025-02-03","cited_by_count":5},{"id":"2502.04043","title":"Probe-Free Low-Rank Activation Intervention","created":"2025-02-06","cited_by_count":5},{"id":"2503.13390","title":"Aligned Probing: Relating Toxic Behavior and Model Internals","created":"2025-03-17","cited_by_count":5},{"id":"2505.15553","title":"Social Bias in Popular Question-Answering Benchmarks","created":"2025-05-21","cited_by_count":5},{"id":"2310.04465","title":"How toxic is antisemitism? Potentials and limitations of automated toxicity scoring for antisemitic online content","created":"2023-10-05","cited_by_count":4},{"id":"2402.04967","title":"Text or Image? What is More Important in Cross-Domain Generalization Capabilities of Hate Meme Detection Models?","created":"2024-02-07","cited_by_count":4},{"id":"2406.08080","title":"AustroTox: A Dataset for Target-Based Austrian German Offensive Language Detection","created":"2024-06-12","cited_by_count":4},{"id":"2409.09741","title":"Benchmarking LLMs in Political Content Text-Annotation: Proof-of-Concept with Toxicity and Incivility Data","created":"2024-09-15","cited_by_count":4},{"id":"2005.04411","title":"Towards Measuring Adversarial Twitter Interactions against Candidates in the US Midterm Elections","created":"2020-05-09","cited_by_count":3},{"id":"2312.17704","title":"TuPy-E: detecting hate speech in Brazilian Portuguese social media with a novel dataset and comprehensive analysis of models","created":"2023-12-29","cited_by_count":3},{"id":"2405.15067","title":"Promoting Constructive Deliberation: Reframing for Receptiveness","created":"2024-05-23","cited_by_count":3},{"id":"2410.00361","title":"PclGPT: A Large Language Model for Patronizing and Condescending Language Detection","created":"2024-10-01","cited_by_count":1},{"id":"2503.15942","title":"Social Media for Activists: Reimagining Safety, Content Presentation, and Workflows","created":"2025-03-20","cited_by_count":1},{"id":"2503.22411","title":"Elite political incivility is rising across democracies","created":"2025-03-28","cited_by_count":1}],"next_cursor":null}