Consistency Guaranteed Causal Graph Recovery with Large Language Models
Keywords: Causal discovery, causal reasoning, large language models, knowledge extraction
TL;DR: This work proposes a novel LLM-based causal graph recovery method, by leveraging the SOTA scientific corpus.
Abstract: Causal graph recovery traditionally relies on statistical estimation of observable variables or individual knowledge, which suffer from data collection biases and knowledge limitations of individuals. Leveraging the broad knowledge in scientific corpus, we propose a novel method for causal graph recovery to deduce causal relationships with the large language models (LLMs) as a knowledge extractor. Our method extracts associational relationships among variables and further eliminates the inconsistent relationship to recover a causal graph using the constraint-based causal discovery methods. Comparing to other LLM-based methods that directly instruct LLMs to do highly complex causal reasoning, our method shows advantages on causal graph quality on benchmark datasets. More importantly, as causal graphs may evolve when new research results emerge, our method shows sensitivity to new evidence in the literature and can provide useful information to update causal graphs accordingly.
Primary Area: causal reasoning
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 13586
Loading