CodeSCM: Causal Analysis for Multi-Modal Code Generation
Mukur Gupta, Noopur Bhatt, Suman Jana
Abstract
In this paper, we propose CodeSCM, a Structural Causal Model (SCM) for analyzing multi-modal code generation using large language models (LLMs). By applying interventions to CodeSCM, we measure the causal effects of different prompt modalities, such as natural language, code, and input-output examples, on the model. CodeSCM introduces latent mediator variables to separate the code and natural language semantics of a multi-modal code generation prompt. Using the principles of Causal Mediation Analysis on these mediators we quantify direct effects representing the model’s spurious leanings. We find that, in addition to natural language instructions, input-output examples significantly influence code generation.
BibTeX
@inproceedings{gupta-etal-2025-codescm,
title = "{C}ode{SCM}: Causal Analysis for Multi-Modal Code Generation",
author = "Gupta, Mukur and
Bhatt, Noopur and
Jana, Suman",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.345/",
pages = "6779--6793",
ISBN = "979-8-89176-189-6"
}