Filling the Gaps: LLMs for Causal Hypothesis Generation

Ivaxi Sheth, Sahar Abdelnabi, Mario Fritz

Keywords: LLMs, hypothesis generation, causal graph

TL;DR: Propose benchmark for hypothesizing missing variables from a causal graph

Abstract: Scientific discovery is a catalyst for human intellectual advances, driven by the cycle of hypothesis generation, experimental design, data evaluation, and iterative assumption refinement. This process, while crucial, is expensive and heavily dependent on the domain knowledge of scientists to generate hypotheses and navigate the scientific cycle. Central to this is causality, the ability to establish the relationship between the cause and the effect. Motivated by the scientific discovery process, in this work, we formulate a novel task where the input is a partial causal graph with missing variables, and the output is a hypothesis about the missing variables to complete the partial graph. We design a benchmark with varying difficulty levels and knowledge assumptions about the causal graph. With the growing interest in using Large Language Models (LLMs) to assist in scientific discovery, we benchmark open-source and closed models on our testbed. We show the strong ability of LLMs to hypothesize the mediation variables between a cause and its effect. In contrast, they underperform in hypothesizing the cause and effect variables themselves. We also observe surprising results where some of the open-source models outperform the closed GPT-4 model.

Primary Area: datasets and benchmarks

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.

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: 7375