Active differentiable structure learning for clinical causal discovery

doi:10.1016/j.knosys.2025.114145

Active differentiable structure learning for clinical causal discovery

2025-07-24

0

PRE

AI

DOI：10.1016/j.knosys.2025.114145

Original

Original request for help

Save

Abstract

En 中文

• We introduce CARD, an LLM-based framework for reward code design and refinement. • Our method lowers human costs, token usage, and training time. • Results show that our method outperforms baselines and exceeds the human oracle.

Keywords:

LLM-based framework

reward code design

training efficiency

human oracle

code refinement

Active differentiable structure learning for clinical causal discovery

Abstract

Journal

Organization