BriefGPT.xyz
Feb, 2024
利用大语言模型高效发现因果图
Efficient Causal Graph Discovery Using Large Language Models
HTML
PDF
Thomas Jiralerspong, Xiaoyin Chen, Yash More, Vedant Shah, Yoshua Bengio
TL;DR
提出了一种利用LLMs进行全因果图发现的新框架,通过广度优先搜索(BFS)方法,使用线性数量的查询,可在不同领域的因果图发现任务中获得具有前沿水平结果的高效性和效果。
Abstract
We propose a novel framework that leverages
llms
for full
causal graph discovery
. While previous LLM-based methods have used a
pairwise query app
→