no code implementations • 16 Oct 2023 • Yingwei Ma, Yue Yu, Shanshan Li, Yu Jiang, Yong Guo, Yuanliang Zhang, Yutao Xie, Xiangke Liao
Meanwhile, while traditional techniques leveraging such semantic information require complex static or dynamic code analysis to obtain features such as data flow and control flow, SeCoT demonstrates that this process can be fully automated via the intrinsic capabilities of LLMs (i. e., in-context learning), while being generalizable and applicable to challenging domains.
1 code implementation • 28 Sep 2023 • Yingwei Ma, Yue Liu, Yue Yu, Yuanliang Zhang, Yu Jiang, Changjian Wang, Shanshan Li
Inspired by the great success of code data in training LLMs, we naturally wonder at which training stage introducing code data can really help LLMs reasoning.
no code implementations • 24 Aug 2022 • Yuanliang Zhang, XiaoFeng Wang, Jinxin Hu, Ke Gao, Chenyi Lei, Fei Fang
we summarize three practical challenges which are not well solved for multi-scenario modeling: (1) Lacking of fine-grained and decoupled information transfer controls among multiple scenarios.