AutoPRM: Automating Procedural Supervision for Multi-Step Reasoning via Controllable Question Decomposition.
Zhaorun Chen, Zhuokai Zhao, Zhihong Zhu, Ruiqi Zhang, Xiang Li, Bhiksha Raj, Huaxiu Yao
Browse the full NAACL paper archive.
Zhaorun Chen, Zhuokai Zhao, Zhihong Zhu, Ruiqi Zhang, Xiang Li, Bhiksha Raj, Huaxiu Yao
Browse the full NAACL paper archive.