Consistent Graph Model Generation with Large Language Models

• Published in: Proceedings (IEEE/ACM International Conference on Software Engineering Companion. Online) pp. 218 - 219
• Main Author: Chen, Boqi
• Format: Conference Proceeding
• Language: English
• Published: IEEE 27.04.2025
• Subjects: Constraint optimization; graph model generation; Large language models; Limiting; Natural languages; Probabilistic logic; Software engineering; Taxonomy
• ISSN: 2574-1934
• DOI: 10.1109/ICSE-Companion66252.2025.00067

Graph model generation from natural language requirements is an essential task in software engineering, for which large language models (LLMs) have become increasingly popular. A key challenge is ensuring that the generated graph models are consistent with domain-specific well-formed constraints. LLM-generated graphs are often partially correct due to inconsistency with the constraints, limiting their practical usage. To address this, we propose a novel abstraction-concretization framework motivated by self-consistency for generating consistent models. Our approach first abstracts candidate models into a probabilistic partial model and then concretizes this abstraction into a consistent graph model. Preliminary evaluations on taxonomy generation demonstrate that our method significantly enhances both the consistency and quality of generated graph models.