Computer Science
Active Prompting with Chain-of-Thought for Large Language Models
S. Diao, P. Wang, et al.
Large language models improve complex reasoning when guided by example-based chain-of-thought prompts. This paper introduces Active-Prompt, an uncertainty-driven method to select the most informative questions for human CoT annotation, yielding superior performance on eight complex reasoning tasks — research conducted by Shizhe Diao, Pengcheng Wang, Yong Lin, Rui Pan, Xiang Liu, and Tong Zhang.
Related Publications
Explore these studies to deepen your understanding of the subject.
