Context-Aware Reasoning On Parametric Knowledge for Inferring Causal Variables

Ivaxi Sheth, Sahar Abdelnabi, Mario Fritz


Abstract
Scientific discovery catalyzes human intellectual advances, driven by the cycle of hypothesis generation, experimental design, evaluation, and assumption refinement. Central to this process is causal inference, uncovering the mechanisms behind observed phenomena. While randomized experiments provide strong inferences, they are often infeasible due to ethical or practical constraints. However, observational studies are prone to confounding or mediating biases. While crucial, identifying such backdoor paths is expensive and heavily depends on scientists’ domain knowledge to generate hypotheses. We introduce a novel benchmark where the objective is to complete a partial causal graph. We design a benchmark with varying difficulty levels with over 4000 queries. We show the strong ability of LLMs to hypothesize the backdoor variables between a cause and its effect. Unlike simple knowledge memorization of fixed associations, our task requires the LLM to reason according to the context of the entire graph.
Anthology ID:
2025.findings-emnlp.1194
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
21881–21918
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.1194/
DOI:
Bibkey:
Cite (ACL):
Ivaxi Sheth, Sahar Abdelnabi, and Mario Fritz. 2025. Context-Aware Reasoning On Parametric Knowledge for Inferring Causal Variables. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 21881–21918, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Context-Aware Reasoning On Parametric Knowledge for Inferring Causal Variables (Sheth et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.1194.pdf
Checklist:
 2025.findings-emnlp.1194.checklist.pdf