{"total":93,"rows":[{"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":"2103.00453","title":"Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP","created":"2021-02-28","cited_by_count":337,"area":null},{"id":"2302.05733","title":"Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks","created":"2023-02-11","cited_by_count":278,"area":null},{"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,"area":null},{"id":"2202.13047","title":"AugESC: Dialogue Augmentation with Large Language Models for Emotional Support Conversation","created":"2022-02-26","cited_by_count":79,"area":null},{"id":"2406.02622","title":"Safeguarding Large Language Models: A Survey","created":"2024-06-03","cited_by_count":78,"area":"safety"},{"id":"2110.08466","title":"On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark","created":"2021-10-16","cited_by_count":73,"area":null},{"id":"2203.07618","title":"Do Language Models Plagiarize?","created":"2022-03-15","cited_by_count":73,"area":null},{"id":"2305.14938","title":"Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark","created":"2023-05-24","cited_by_count":63,"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":"2311.16153","title":"Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications","created":"2023-11-07","cited_by_count":54,"area":null},{"id":"2109.09483","title":"ConvAbuse: Data, Analysis, and Benchmarks for Nuanced Abuse Detection in Conversational AI","created":"2021-09-20","cited_by_count":46,"area":null},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"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":"2210.14169","title":"Weakly Supervised Data Augmentation Through Prompting for Dialogue Understanding","created":"2022-10-25","cited_by_count":32,"area":null},{"id":"2302.06503","title":"Ground(less) Truth: A Causal Framework for Proxy Labels in Human-Algorithm Decision-Making","created":"2023-02-13","cited_by_count":25,"area":null},{"id":"2109.04673","title":"DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization","created":"2021-09-10","cited_by_count":21,"area":null},{"id":"2307.09209","title":"Automated Ableism: An Exploration of Explicit Disability Biases in Sentiment and Toxicity Analysis Models","created":"2023-07-18","cited_by_count":20,"area":null},{"id":"2103.14916","title":"Abuse is Contextual, What about NLP? The Role of Context in Abusive Language Annotation and Detection","created":"2021-03-27","cited_by_count":19,"area":null},{"id":"2110.04419","title":"Detecting Community Sensitive Norm Violations in Online Conversations","created":"2021-10-09","cited_by_count":18,"area":null},{"id":"2308.11490","title":"Can Authorship Representation Learning Capture Stylistic Features?","created":"2023-08-22","cited_by_count":17,"area":null},{"id":"2409.14740","title":"ToxiCraft: A Novel Framework for Synthetic Generation of Harmful Information","created":"2024-09-23","cited_by_count":17,"area":"safety"},{"id":"2311.05074","title":"GRASP: A Disagreement Analysis Framework to Assess Group Associations in Perspectives","created":"2023-11-09","cited_by_count":16,"area":"safety"},{"id":"2106.06213","title":"CONDA: a CONtextual Dual-Annotated dataset for in-game toxicity understanding and detection","created":"2021-06-11","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":"2309.14517","title":"Watch Your Language: Investigating Content Moderation with Large Language Models","created":"2023-09-25","cited_by_count":14,"area":null},{"id":"2311.09585","title":"LifeTox: Unveiling Implicit Toxicity in Life Advice","created":"2023-11-16","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":"2111.13259","title":"Identification of Bias Against People with Disabilities in Sentiment Analysis and Toxicity Detection Models","created":"2021-11-25","cited_by_count":13,"area":null},{"id":"2408.15488","title":"Legilimens: Practical and Unified Content Moderation for Large Language Model Services","created":"2024-08-28","cited_by_count":13,"area":"safety"},{"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":"2210.00465","title":"Assessing the impact of contextual information in hate speech detection","created":"2022-10-02","cited_by_count":10,"area":null},{"id":"2311.07879","title":"Toxicity Detection is NOT all you Need: Measuring the Gaps to Supporting Volunteer Content Moderators","created":"2023-11-14","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":"2505.24341","title":"Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings","created":"2025-05-30","cited_by_count":10,"area":null},{"id":"2106.02183","title":"Towards Equal Gender Representation in the Annotations of Toxic Language Detection","created":"2021-06-04","cited_by_count":9,"area":null},{"id":"2111.12447","title":"Revisiting Contextual Toxicity Detection in Conversations","created":"2021-11-24","cited_by_count":8,"area":null},{"id":"2411.12174","title":"Just KIDDIN: Knowledge Infusion and Distillation for Detection of INdecent Memes","created":"2024-11-19","cited_by_count":8,"area":null},{"id":"2305.05816","title":"Best-Effort Adaptation","created":"2023-05-10","cited_by_count":7,"area":null},{"id":"2102.12254","title":"NLRG at SemEval-2021 Task 5: Toxic Spans Detection Leveraging BERT-based Token Classification and Span Prediction Techniques","created":"2021-02-24","cited_by_count":6,"area":null},{"id":"2109.08805","title":"BERT-Beta: A Proactive Probabilistic Approach to Text Moderation","created":"2021-09-18","cited_by_count":6,"area":null},{"id":"2111.10223","title":"Toxicity Detection can be Sensitive to the Conversational Context","created":"2021-11-19","cited_by_count":6,"area":null},{"id":"2509.08653","title":"Generative Data Refinement: Just Ask for Better Data","created":"2025-09-10","cited_by_count":6,"area":null},{"id":"2204.06389","title":"CRUSH: Contextually Regularized and User anchored Self-supervised Hate speech Detection","created":"2022-04-13","cited_by_count":5,"area":null},{"id":"2305.12542","title":"ToxBuster: In-game Chat Toxicity Buster with BERT","created":"2023-05-21","cited_by_count":5,"area":null},{"id":"2310.18330","title":"Towards Detecting Contextual Real-Time Toxicity for In-Game Chat","created":"2023-10-20","cited_by_count":5,"area":null},{"id":"2106.07192","title":"Automatic Document Sketching: Generating Drafts from Analogous Texts","created":"2021-06-14","cited_by_count":4,"area":null},{"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,"area":null},{"id":"2504.18673","title":"Can Third-parties Read Our Emotions?","created":"2025-04-25","cited_by_count":4,"area":null},{"id":"2606.28725","title":"DriftGuard: Safety-Aware Multi-Monitor Detection and Selective Adaptation for Evolving Toxicity Moderation","created":"2026-06-27","cited_by_count":4,"area":null},{"id":"2112.09986","title":"Leveraging Transformers for Hate Speech Detection in Conversational Code-Mixed Tweets","created":"2021-12-18","cited_by_count":3,"area":null},{"id":"2206.08445","title":"Enriching Abusive Language Detection with Community Context","created":"2022-06-16","cited_by_count":3,"area":null},{"id":"2305.10731","title":"Analyzing Norm Violations in Live-Stream Chat","created":"2023-05-18","cited_by_count":3,"area":null},{"id":"2306.00121","title":"Multilingual Multi-Figurative Language Detection","created":"2023-05-31","cited_by_count":3,"area":null},{"id":"2402.02975","title":"Putting Context in Context: the Impact of Discussion Structure on Text Classification","created":"2024-02-05","cited_by_count":3,"area":null},{"id":"2409.13705","title":"Debiasing Text Safety Classifiers through a Fairness-Aware Ensemble","created":"2024-09-05","cited_by_count":3,"area":"safety"},{"id":"2505.18927","title":"Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2507.18580","title":"System Report for CCL25-Eval Task 10: SRAG-MAV for Fine-Grained Chinese Hate Speech Recognition","created":"2025-07-24","cited_by_count":3,"area":null},{"id":"2510.13351","title":"Protect: Towards Robust Guardrailing Stack for Trustworthy Enterprise LLM Systems","created":"2025-10-15","cited_by_count":3,"area":"safety"},{"id":"2210.12233","title":"TCAB: A Large-Scale Text Classification Attack Benchmark","created":"2022-10-21","cited_by_count":2,"area":null},{"id":"2303.11184","title":"Conversation Modeling to Predict Derailment","created":"2023-03-20","cited_by_count":2,"area":null},{"id":"2411.08135","title":"On the Role of Speech Data in Reducing Toxicity Detection Bias","created":"2024-11-12","cited_by_count":2,"area":null},{"id":"2503.16505","title":"Designing Synthetic Discussion Generation Systems: A Case Study for Online Facilitation","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2203.02392","title":"Beyond Plain Toxic: Detection of Inappropriate Statements on Flammable Topics for the Russian Language","created":"2022-03-04","cited_by_count":1,"area":null},{"id":"2307.05728","title":"Towards A Scalable Solution for Improving Multi-Group Fairness in Compositional Classification","created":"2023-07-11","cited_by_count":1,"area":null},{"id":"2308.14253","title":"The Promise and Peril of Artificial Intelligence -- Violet Teaming Offers a Balanced Path Forward","created":"2023-08-28","cited_by_count":1,"area":null},{"id":"2310.02357","title":"On the definition of toxicity in NLP","created":"2023-10-03","cited_by_count":1,"area":null},{"id":"2407.09861","title":"A Systematic Survey of Natural Language Processing for the Greek Language","created":"2024-07-13","cited_by_count":1,"area":null},{"id":"2412.17533","title":"Behind Closed Words: Creating and Investigating the forePLay Annotated Dataset for Polish Erotic Discourse","created":"2024-12-23","cited_by_count":1,"area":null},{"id":"2504.01902","title":"Graphically Speaking: Unmasking Abuse in Social Media with Conversation Insights","created":"2025-04-02","cited_by_count":1,"area":null},{"id":"2504.15439","title":"Combating Toxic Language: A Review of LLM-Based Strategies for Software Engineering","created":"2025-04-21","cited_by_count":1,"area":null},{"id":"2505.17144","title":"MDIT-Bench: Evaluating the Dual-Implicit Toxicity in Large Multimodal Models","created":"2025-05-22","cited_by_count":1,"area":"mllm"},{"id":"2506.21613","title":"ChildGuard: A Specialized Dataset for Combatting Child-Targeted Hate Speech","created":"2025-06-21","cited_by_count":1,"area":null},{"id":"2507.05455","title":"ModelCitizens: Representing Community Voices in Online Safety","created":"2025-07-07","cited_by_count":1,"area":null},{"id":"2508.10031","title":"Context Misleads LLMs: The Role of Context Filtering in Maintaining Safe Alignment of LLMs","created":"2025-08-09","cited_by_count":1,"area":"alignment"},{"id":"2412.04046","title":"Hostility Detection in UK Politics: A Dataset on Online Abuse Targeting MPs","created":"2024-12-05","cited_by_count":0,"area":null},{"id":"2503.16072","title":"Toxicity Is a Property of Communicative Events: A Contextual Stress Measurement Framework for NLP","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2504.17653","title":"Towards a comprehensive taxonomy of online abusive language informed by machine leaning","created":"2025-04-24","cited_by_count":0,"area":null},{"id":"2505.12767","title":"Language Models That Walk the Talk: A Framework for Formal Fairness Certificates","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2506.16190","title":"Web(er) of Hate: A Survey on How Hate Speech Is Typed","created":"2025-06-19","cited_by_count":0,"area":null},{"id":"2509.05719","title":"Exploring Subjective Tasks in Farsi: A Survey Analysis and Evaluation of Language Models","created":"2025-09-06","cited_by_count":0,"area":null},{"id":"2509.09043","title":"Stated Preference for Interaction and Continued Engagement (SPICE): Evaluating an LLM's Willingness to Re-engage in Conversation","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2510.05864","title":"On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2510.15685","title":"Leveraging LLMs for Context-Aware Implicit Textual and Multimodal Hate Speech Detection","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2512.09563","title":"System Report for CCL25-Eval Task 10: Prompt-Driven Large Language Model Merge for Fine-Grained Chinese Hate Speech Detection","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2601.06907","title":"Fine-grained Verbal Attack Detection via a Hierarchical Divide-and-Conquer Framework","created":"2026-01-11","cited_by_count":0,"area":null},{"id":"2604.17301","title":"RoTRAG: Rule of Thumb Reasoning for Conversation Harm Detection with Retrieval-Augmented Generation","created":"2026-04-19","cited_by_count":0,"area":"lr"},{"id":"2605.09739","title":"The Silent Vote: Improving Zero-Shot LLM Reliability by Aggregating Semantic Neighborhoods","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2606.27981","title":"ToxiREX: A Dataset on Toxic REasoning in ConteXt","created":"2026-06-26","cited_by_count":0,"area":"lr"},{"id":"2608.25605","title":"From Specialization to Generalization: Instruction-tuned LLMs for Robust Harmful Content Mitigation","created":"2026-08-26","cited_by_count":0,"area":"safety"},{"id":"2609.00361","title":"Detoxifying Toxic Communication: A Design Science Approach to Responsible AI","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.17549","title":"Do Social Patterns Hold in Synthetic Data? Analyzing Cyberbullying Dynamics in LLM-Generated and Authentic Dialogues","created":"2026-07-15","cited_by_count":0,"area":"synth"},{"id":"2609.20059","title":"AI Should Facilitate Democratic Deliberation at Scale","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}