{"total":17,"rows":[{"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":"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":"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":"2206.06423","title":"Hate Speech and Counter Speech Detection: Conversational Context Does Matter","created":"2022-06-13","cited_by_count":32,"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":"2111.12447","title":"Revisiting Contextual Toxicity Detection in Conversations","created":"2021-11-24","cited_by_count":8,"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":"2307.02763","title":"Your spouse needs professional help: Determining the Contextual Appropriateness of Messages through Modeling Social Relationships","created":"2023-07-06","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":"2311.04345","title":"A Taxonomy of Rater Disagreements: Surveying Challenges & Opportunities from the Perspective of Annotating Online Toxicity","created":"2023-11-07","cited_by_count":4,"area":null},{"id":"2305.10731","title":"Analyzing Norm Violations in Live-Stream Chat","created":"2023-05-18","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":"2310.02357","title":"On the definition of toxicity in NLP","created":"2023-10-03","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":"2405.11030","title":"The Unappreciated Role of Intent in Algorithmic Moderation of Social Media Content","created":"2024-05-17","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":"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}],"next_cursor":null}