{"total":18,"rows":[{"id":"2307.11729","title":"OUTFOX: LLM-Generated Essay Detection Through In-Context Learning with Adversarially Generated Examples","created":"2023-07-21","cited_by_count":80,"area":null},{"id":"2201.06025","title":"COLD: A Benchmark for Chinese Offensive Language Detection","created":"2022-01-16","cited_by_count":76,"area":null},{"id":"2205.11503","title":"Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Models","created":"2022-05-23","cited_by_count":49,"area":null},{"id":"2205.12390","title":"Toxicity Detection with Generative Prompt-based Inference","created":"2022-05-24","cited_by_count":35,"area":null},{"id":"2210.10040","title":"The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarks","created":"2022-10-18","cited_by_count":31,"area":null},{"id":"2404.11023","title":"Advancing Social Intelligence in AI Agents: Technical Challenges and Open Questions","created":"2024-04-17","cited_by_count":22,"area":null},{"id":"2310.12127","title":"A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation","created":"2023-10-18","cited_by_count":19,"area":null},{"id":"2302.07388","title":"Adding Instructions during Pretraining: Effective Way of Controlling Toxicity in Language Models","created":"2023-02-14","cited_by_count":16,"area":null},{"id":"2302.07371","title":"BiasTestGPT: Using ChatGPT for Social Bias Testing of Language Models","created":"2023-02-14","cited_by_count":8,"area":null},{"id":"2211.11798","title":"Can You Label Less by Using Out-of-Domain Data? Active & Transfer Learning with Few-shot Instructions","created":"2022-11-21","cited_by_count":7,"area":null},{"id":"2406.09977","title":"Disentangling Dialect from Social Bias via Multitask Learning to Improve Fairness","created":"2024-06-14","cited_by_count":1,"area":null},{"id":"2410.00477","title":"ViDAS: Vision-based Danger Assessment and Scoring","created":"2024-10-01","cited_by_count":1,"area":null},{"id":"2506.09259","title":"Self-Anchored Attention Model for Sample-Efficient Classification of Prosocial Text Chat","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2508.05938","title":"Prosocial Behavior Detection in Player Game Chat: From Aligning Human-AI Definitions to Efficient Annotation at Scale","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2410.19642","title":"VARS: Vision-based Assessment of Risk in Security Systems","created":"2024-10-25","cited_by_count":0,"area":null},{"id":"2512.00556","title":"Bias Testing and Mitigation in Black Box LLMs using Metamorphic Relations","created":"2025-11-29","cited_by_count":0,"area":null},{"id":"2601.10460","title":"Contextual StereoSet: Stress-Testing Bias Alignment Robustness in Large Language Models","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2603.15654","title":"Discovering the Hidden Role of Gini Index In Prompt-based Classification","created":"2026-03-07","cited_by_count":0,"area":null}],"next_cursor":null}