CausalPrompt: Enhancing LLMs with weakly supervised causal reasoning for robust performance in non-language tasks

We introduce CausalPrompt, a framework that equips LLMs with weakly supervised causal reasoning to improve robustness on non-language tasks. The method leverages causal cues and domain structure to guide prompting and decision-making, yielding stronger performance under distribution shifts pertinent to climate and infrastructure applications.

Authors

Tung-Wei Lin

Vanshaj Khattar

Yuxuan Huang

Junho Hong

Ruoxi Jia

Chen-Ching Liu

Alberto Sangiovanni-Vincentelli

Ming Jin

Published

January 1, 2024