2 papers
cs.AI2026
OpenFC: Learning Verification Policies towards Open-Search Fact Checking
Xinming Wang, Kaixiang Qiu, Yansong Lin +5
Open-search fact checking is not merely retrieval followed by classification, but a sequential decision problem in which every query, source visit, and stopping decision reshapes t…
cs.CL2026
Dense Is Not Enough: Hierarchical Supervision Allocation for Long-Horizon On-Policy Distillation
Yuhao Sun, Binrui Wu, Zhuoer Xu +5
On-policy distillation (OPD) transfers the capabilities of a large language model to a smaller student by providing teacher supervision on the student's own rollouts. In long-horiz…