Leveraging large language models for causal discovery: a constraint-based, argumentation-driven approach
File(s)
Accepted version
Author(s)
Li, Zihao
Russo, Fabrizio
Type
Conference Paper
Abstract
Causal discovery seeks to uncover causal relations from data, typically represented as causal graphs, and is essential for predicting the effects of interventions. While expert knowledge is required to construct principled causal graphs, many statistical methods have been proposed to leverage observational data with varying formal guarantees. Causal Assumption-based Argumentation (ABA) is a framework that uses symbolic reasoning to ensure correspondence between input constraints and output graphs, while offering a principled way to combine data and expertise. We explore the use of large language models (LLMs) as imperfect experts, eliciting semantic structural priors from variable names and descriptions and integrating them with statistical evidence through Causal ABA. We introduce an evaluation protocol to mitigate memorisation bias when assessing LLMs for causal discovery and experiments on semantically
grounded synthetic graphs, as well as on standard benchmarks, show state-of-the-art performance.
grounded synthetic graphs, as well as on standard benchmarks, show state-of-the-art performance.
Date Acceptance
2026-06-01
Citation
Proceedings of Machine Learning Research
ISSN
2640-3498
Publisher
MLResearchPress
Journal / Book Title
Proceedings of Machine Learning Research
Copyright Statement
Subject to copyright. This paper is embargoed until publication.
Source
42nd Conference on Uncertainty in Artificial Intelligence (uai 2026)
Publication Status
Accepted
Start Date
2026-08-17
Finish Date
2026-08-21
Coverage Spatial
Amsterdam, Netherlands