#machine learning
Sep 2025
MuPlon: Multi-Path Causal Optimization for Claim Verification through Controlling Confounding
This work proposes a novel framework, Multi-Path Causal Optimization (MuPlon), which combines a dual causal intervention strategy, consisting of the back-door path and front-door path, and demonstrates that MuPlon outperforms existing methods and achieves state-of-the-art performance.
Hanghui Guo, Shi-Min Di, P. D. Meo et al.
· arXiv.org · 0 citations