MolEval: An Evaluation Toolkit for Molecular Embeddings via LLMs

Shaghayegh Sadeghi, Ali Forooghi, Jianguo Lu, Alioune Ngom

Keywords: Large Language Models, Molecular Embeddings, LLaMA, GPT, Molecular Property Prediction, Evaluation Toolkit

Abstract: Inspired by SentEval and MTEB for sentence embeddings and DeepChem for molecular machine learning, we introduce MolEval. MolEval tackles the issue of evaluating large language models (LLMs) embeddings, which are traditionally expensive to execute on standard computing hardware. It achieves this by offering a repository of pre-computed molecule embeddings alongside a versatile platform that facilitates the evaluation of any embeddings derived from molecular structures. This approach not only streamlines the assessment process but also makes it more accessible to researchers and practitioners in the field.

Submission Number: 17