Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration
Year: 2026
Type: conference-paper
Abstract: Yang Zhao, Yangou Ouyang, Xiao Ding, Hepeng Wang, Bibo Cai, Kai Xiong, Jinglong Gao, Zhouhao Sun, Li Du, Bing Qin, Ting Liu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.
Institution: Harbin Institute of Technology
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Award: G4442529403
OpenAlex ID: W7166856263
