{"total":96,"rows":[{"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":"2310.11667","title":"SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents","created":"2023-10-18","cited_by_count":367,"area":"agents"},{"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":"2405.20947","title":"OR-Bench: An Over-Refusal Benchmark for Large Language Models","created":"2024-05-31","cited_by_count":244,"area":"alignment"},{"id":"2109.07445","title":"Challenges in Detoxifying Language Models","created":"2021-09-15","cited_by_count":169,"area":null},{"id":"2305.14456","title":"Having Beer after Prayer? Measuring Cultural Bias in Large Language Models","created":"2023-05-23","cited_by_count":153,"area":null},{"id":"2311.12786","title":"Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks","created":"2023-11-21","cited_by_count":115,"area":null},{"id":"2205.12688","title":"ProsocialDialog: A Prosocial Backbone for Conversational Agents","created":"2022-05-25","cited_by_count":109,"area":"agents"},{"id":"2104.06390","title":"Detoxifying Language Models Risks Marginalizing Minority Voices","created":"2021-04-13","cited_by_count":107,"area":null},{"id":"2501.18492","title":"GuardReasoner: Towards Reasoning-based LLM Safeguards","created":"2025-01-30","cited_by_count":100,"area":"lr"},{"id":"2308.10149","title":"A Survey on Fairness in Large Language Models","created":"2023-08-20","cited_by_count":95,"area":null},{"id":"2111.07408","title":"Time Waits for No One! Analysis and Challenges of Temporal Misalignment","created":"2021-11-14","cited_by_count":91,"area":null},{"id":"2109.05184","title":"MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets","created":"2021-09-11","cited_by_count":86,"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":"2504.17704","title":"Safety in Large Reasoning Models: A Survey","created":"2025-04-24","cited_by_count":64,"area":"lr"},{"id":"2202.00126","title":"Handling Bias in Toxic Speech Detection: A Survey","created":"2022-01-26","cited_by_count":61,"area":null},{"id":"2403.05020","title":"Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMs","created":"2024-03-08","cited_by_count":59,"area":null},{"id":"2108.11830","title":"Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts","created":"2021-08-26","cited_by_count":56,"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":"2212.08011","title":"Multi-VALUE: A Framework for Cross-Dialectal English NLP","created":"2022-12-15","cited_by_count":53,"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":"2407.05557","title":"$R^2$-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoning","created":"2024-07-08","cited_by_count":43,"area":"lr"},{"id":"2109.02593","title":"General-Purpose Question-Answering with Macaw","created":"2021-09-06","cited_by_count":40,"area":null},{"id":"2203.12574","title":"Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal","created":"2022-03-23","cited_by_count":40,"area":"distill"},{"id":"2202.08011","title":"Towards Identifying Social Bias in Dialog Systems: Frame, Datasets, and Benchmarks","created":"2022-02-16","cited_by_count":36,"area":null},{"id":"2305.14291","title":"Evaluation of African American Language Bias in Natural Language Generation","created":"2023-05-23","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":"2210.04492","title":"Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization","created":"2022-10-10","cited_by_count":33,"area":null},{"id":"2104.06999","title":"Detecting Cross-Geographic Biases in Toxicity Modeling on Social Media","created":"2021-04-14","cited_by_count":31,"area":null},{"id":"2204.01734","title":"On Explaining Multimodal Hateful Meme Detection Models","created":"2022-04-04","cited_by_count":29,"area":null},{"id":"2410.23687","title":"Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey","created":"2024-10-31","cited_by_count":23,"area":"mllm"},{"id":"2501.00192","title":"MLLM-as-a-Judge for Image Safety without Human Labeling","created":"2024-12-31","cited_by_count":23,"area":null},{"id":"2506.09996","title":"From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring","created":"2025-06-11","cited_by_count":22,"area":"alignment"},{"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":"2405.09373","title":"PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models","created":"2024-05-15","cited_by_count":20,"area":null},{"id":"2502.12858","title":"Rejected Dialects: Biases Against African American Language in Reward Models","created":"2025-02-18","cited_by_count":20,"area":"alignment"},{"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":"2107.04212","title":"Measuring and Improving Model-Moderator Collaboration using Uncertainty Estimation","created":"2021-07-09","cited_by_count":18,"area":null},{"id":"2210.07455","title":"Controlling Bias Exposure for Fair Interpretable Predictions","created":"2022-10-14","cited_by_count":18,"area":null},{"id":"2105.12449","title":"LMMS Reloaded: Transformer-based Sense Embeddings for Disambiguation and Beyond","created":"2021-05-26","cited_by_count":17,"area":null},{"id":"2405.06346","title":"Akal Badi ya Bias: An Exploratory Study of Gender Bias in Hindi Language Technology","created":"2024-05-10","cited_by_count":17,"area":null},{"id":"2307.16680","title":"On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook","created":"2023-07-31","cited_by_count":15,"area":"diffusion"},{"id":"2204.02261","title":"Improving Generalizability in Implicitly Abusive Language Detection with Concept Activation Vectors","created":"2022-04-05","cited_by_count":14,"area":null},{"id":"2206.13757","title":"Flexible text generation for counterfactual fairness probing","created":"2022-06-28","cited_by_count":13,"area":null},{"id":"2302.06541","title":"Towards Agile Text Classifiers for Everyone","created":"2023-02-13","cited_by_count":13,"area":null},{"id":"2305.13406","title":"DADA: Dialect Adaptation via Dynamic Aggregation of Linguistic Rules","created":"2023-05-22","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":"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":"2109.04624","title":"Style Pooling: Automatic Text Style Obfuscation for Improved Classification Fairness","created":"2021-09-10","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":"2210.10329","title":"Language Detoxification with Attribute-Discriminative Latent Space","created":"2022-10-19","cited_by_count":11,"area":null},{"id":"2408.14845","title":"AAVENUE: Detecting LLM Biases on NLU Tasks in AAVE via a Novel Benchmark","created":"2024-08-27","cited_by_count":11,"area":null},{"id":"2204.05424","title":"A Call for Clarity in Beam Search: How It Works and When It Stops","created":"2022-04-11","cited_by_count":10,"area":null},{"id":"2407.03160","title":"SOS! Soft Prompt Attack Against Open-Source Large Language Models","created":"2024-07-03","cited_by_count":10,"area":"safety"},{"id":"2407.11733","title":"How Are LLMs Mitigating Stereotyping Harms? Learning from Search Engine Studies","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2308.02080","title":"Causality Guided Disentanglement for Cross-Platform Hate Speech Detection","created":"2023-08-03","cited_by_count":9,"area":"safety"},{"id":"2311.00915","title":"Task-Agnostic Low-Rank Adapters for Unseen English Dialects","created":"2023-11-02","cited_by_count":9,"area":null},{"id":"2205.07233","title":"Mitigating Toxic Degeneration with Empathetic Data: Exploring the Relationship Between Toxicity and Empathy","created":"2022-05-15","cited_by_count":8,"area":null},{"id":"2402.08225","title":"Improving Black-box Robustness with In-Context Rewriting","created":"2024-02-13","cited_by_count":8,"area":null},{"id":"2106.07240","title":"Mitigating Biases in Toxic Language Detection through Invariant Rationalization","created":"2021-06-14","cited_by_count":7,"area":null},{"id":"2205.06621","title":"Analyzing Hate Speech Data along Racial, Gender and Intersectional Axes","created":"2022-05-13","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":"2311.09993","title":"Generative AI for Hate Speech Detection: Evaluation and Findings","created":"2023-11-16","cited_by_count":7,"area":null},{"id":"2402.12212","title":"Polarization of Autonomous Generative AI Agents Under Echo Chambers","created":"2024-02-19","cited_by_count":7,"area":"agents"},{"id":"2406.00046","title":"Hate Speech Detection with Generalizable Target-aware Fairness","created":"2024-05-28","cited_by_count":7,"area":null},{"id":"2406.06559","title":"Harnessing Business and Media Insights with Large Language Models","created":"2024-06-02","cited_by_count":7,"area":null},{"id":"2410.22587","title":"Toxicity of the Commons: Curating Open-Source Pre-Training Data","created":"2024-10-29","cited_by_count":7,"area":null},{"id":"2108.11056","title":"Social Norm Bias: Residual Harms of Fairness-Aware Algorithms","created":"2021-08-25","cited_by_count":6,"area":null},{"id":"2302.02038","title":"Rating Sentiment Analysis Systems for Bias through a Causal Lens","created":"2023-02-04","cited_by_count":6,"area":null},{"id":"2407.01850","title":"Purple-teaming LLMs with Adversarial Defender Training","created":"2024-07-01","cited_by_count":6,"area":"safety"},{"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":"2201.06384","title":"Cyberbullying Classifiers are Sensitive to Model-Agnostic Perturbations","created":"2022-01-17","cited_by_count":5,"area":null},{"id":"2205.12391","title":"Toward Understanding Bias Correlations for Mitigation in NLP","created":"2022-05-24","cited_by_count":5,"area":null},{"id":"2302.06598","title":"Gradient-Based Automated Iterative Recovery for Parameter-Efficient Tuning","created":"2023-02-13","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":"2112.02265","title":"\"Stop Asian Hate!\" : Refining Detection of Anti-Asian Hate Speech During the COVID-19 Pandemic","created":"2021-12-04","cited_by_count":4,"area":null},{"id":"2210.07595","title":"The State of Profanity Obfuscation in Natural Language Processing","created":"2022-10-14","cited_by_count":4,"area":null},{"id":"2302.06801","title":"Backdoor Learning for NLP: Recent Advances, Challenges, and Future Research Directions","created":"2023-02-14","cited_by_count":4,"area":"safety"},{"id":"2309.14146","title":"Examining Temporal Bias in Abusive Language Detection","created":"2023-09-25","cited_by_count":4,"area":null},{"id":"2310.00347","title":"Unlocking Bias Detection: Leveraging Transformer-Based Models for Content Analysis","created":"2023-09-30","cited_by_count":4,"area":null},{"id":"2505.20875","title":"Trans-EnV: A Framework for Evaluating the Linguistic Robustness of LLMs Against English Varieties","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2205.08001","title":"Towards Debiasing Translation Artifacts","created":"2022-05-16","cited_by_count":3,"area":null},{"id":"2206.08978","title":"Towards a Deep Multi-layered Dialectal Language Analysis: A Case Study of African-American English","created":"2022-06-03","cited_by_count":3,"area":null},{"id":"2109.02734","title":"Detecting Inspiring Content on Social Media","created":"2021-09-06","cited_by_count":2,"area":null},{"id":"2112.08346","title":"Simple Text Detoxification by Identifying a Linear Toxic Subspace in Language Model Embeddings","created":"2021-12-15","cited_by_count":2,"area":null},{"id":"2601.09250","title":"When to Invoke: Refining LLM Fairness with Toxicity Assessment","created":"2026-01-14","cited_by_count":2,"area":null},{"id":"2309.08624","title":"Challenges in Annotating Datasets to Quantify Bias in Under-represented Society","created":"2023-09-11","cited_by_count":1,"area":null},{"id":"2311.18215","title":"Automatic Construction of a Korean Toxic Instruction Dataset for Ethical Tuning of Large Language Models","created":"2023-11-30","cited_by_count":1,"area":null},{"id":"2203.11401","title":"Suum Cuique: Studying Bias in Taboo Detection with a Community Perspective","created":"2022-03-22","cited_by_count":0,"area":null},{"id":"2211.04364","title":"NaturalAdversaries: Can Naturalistic Adversaries Be as Effective as Artificial Adversaries?","created":"2022-11-08","cited_by_count":0,"area":null},{"id":"2307.03385","title":"AI-UPV at EXIST 2023 -- Sexism Characterization Using Large Language Models Under The Learning with Disagreements Regime","created":"2023-07-07","cited_by_count":0,"area":null},{"id":"2601.17764","title":"Cross-Lingual Probing and Community-Grounded Analysis of Gender Bias in Low-Resource Bengali","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2604.16845","title":"DART: Mitigating Harm Drift in Difference-Aware LLMs via Distill-Audit-Repair Training","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2605.10639","title":"Navigating the Sea of LLM Evaluation: Investigating Bias in Toxicity Benchmarks","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.29659","title":"Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content","created":"2026-05-28","cited_by_count":0,"area":"safety"}],"next_cursor":null}