MolRAG: Unlocking the Power of Large Language Models for Molecular Property Prediction
Ziting Xian, Jiawei Gu, Lingbo Li, Shangsong Liang
Abstract
Recent LLMs exhibit limited effectiveness on molecular property prediction task due to the semantic gap between molecular representations and natural language, as well as the lack of domain-specific knowledge. To address these challenges, we propose MolRAG, a Retrieval-Augmented Generation framework integrating Chain-of-Thought reasoning for molecular property prediction. MolRAG operates by retrieving structurally analogous molecules as contextual references to guide stepwise knowledge reasoning through chemical structure-property relationships. This dual mechanism synergizes molecular similarity analysis with structured inference, while generating human-interpretable rationales grounded in domain knowledge. Experimental results show MolRAG outperforms pre-trained LLMs on four datasets, and even matches supervised methods, achieving performance gains of 1.1%–45.7% over direct prediction approaches, demonstrating versatile effectiveness. Our code is available at https://github.com/AcaciaSin/MolRAG.
BibTeX
@inproceedings{xian-etal-2025-molrag,
title = "{M}ol{RAG}: Unlocking the Power of Large Language Models for Molecular Property Prediction",
author = "Xian, Ziting and
Gu, Jiawei and
Li, Lingbo and
Liang, Shangsong",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.755/",
doi = "10.18653/v1/2025.acl-long.755",
pages = "15513--15531",
ISBN = "979-8-89176-251-0"
}