ProCI uses LLMs to iteratively generate and impute hidden confounders, then validates them with a conditional independence test to improve treatment effect estimation.
Discovery of the hidden world with large language models, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Mitigating Hidden Confounding by Progressive Confounder Imputation via Large Language Models
ProCI uses LLMs to iteratively generate and impute hidden confounders, then validates them with a conditional independence test to improve treatment effect estimation.