Peiran Li, Jan Fillies, Adrian Paschke. ToxiGAN: Toxic Data Augmentation via LLM-Guided Directional Adversarial Generation. In Vera Demberg, Kentaro Inui, Lluís Marquez, editors, Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2026 - Volume 1: Long Papers, Rabat, Morocco, March 24-29, 2026. pages 4029-4044, Association for Computational Linguistics, 2026. [doi]
Abstract is missing.