Yuexiao Liu, Lijun Li, Xingjun Wang, Jing Shao. HarmRLVR: Weaponizing Verifiable Rewards for Harmful LLM Alignment. In Maria Liakata, Viviane P. Moreira, Jiajun Zhang 0001, David Jurgens, editors, Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2026, San Diego, California, United States, July 2-7, 2026. pages 11461-11479, Association for Computational Linguistics, 2026. [doi]
Abstract is missing.