3 papers
cs.CL2025
Unbiased Reasoning for Knowledge-Intensive Tasks in Large Language Models via Conditional Front-Door Adjustment
Bo Zhao, Yinghao Zhang, Ziqi Xu +5
Large Language Models (LLMs) have shown impressive capabilities in natural language processing but still struggle to perform well on knowledge-intensive tasks that require deep rea…
cs.CL2024
Counterfactual Samples Constructing and Training for Commonsense Statements Estimation
Chong Liu, Zaiwen Feng, Lin Liu +5
Plausibility Estimation (PE) plays a crucial role for enabling language models to objectively comprehend the real world. While large language models (LLMs) demonstrate remarkable c…
cs.LG2024
Causal Effect Estimation using identifiable Variational AutoEncoder with Latent Confounders and Post-Treatment Variables
Yang Xie, Ziqi Xu, Debo Cheng +4
Estimating causal effects from observational data is challenging, especially in the presence of latent confounders. Much work has been done on addressing this challenge, but most o…