MolLangBench: A Comprehensive Benchmark for Language-Prompted Molecular Structure Recognition, Editing, and Generation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Cai, Feiyang, Bai, Jiahui, Tang, Tao, He, Guijuan, Luo, Joshua, Zhu, Tianyu, Pilla, Srikanth, Li, Gang, Liu, Ling, Luo, Feng
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917357202440192
author Cai, Feiyang
Bai, Jiahui
Tang, Tao
He, Guijuan
Luo, Joshua
Zhu, Tianyu
Pilla, Srikanth
Li, Gang
Liu, Ling
Luo, Feng
author_facet Cai, Feiyang
Bai, Jiahui
Tang, Tao
He, Guijuan
Luo, Joshua
Zhu, Tianyu
Pilla, Srikanth
Li, Gang
Liu, Ling
Luo, Feng
contents Precise recognition, editing, and generation of molecules are essential prerequisites for both chemists and AI systems tackling various chemical tasks. We present MolLangBench, a comprehensive benchmark designed to evaluate fundamental molecule-language interface tasks: language-prompted molecular structure recognition, editing, and generation. To ensure high-quality, unambiguous, and deterministic outputs, we construct the recognition tasks using automated cheminformatics tools, and curate editing and generation tasks through rigorous expert annotation and validation. MolLangBench supports the evaluation of models that interface language with different molecular representations, including linear strings, molecular images, and molecular graphs. Evaluations of state-of-the-art models reveal significant limitations: the strongest model (GPT-5) achieves $86.2\%$ and $85.5\%$ accuracy on recognition and editing tasks, which are intuitively simple for humans, and performs even worse on the generation task, reaching only $43.0\%$ accuracy. These results highlight the shortcomings of current AI systems in handling even preliminary molecular recognition and manipulation tasks. We hope MolLangBench will catalyze further research toward more effective and reliable AI systems for chemical applications.The dataset and code can be accessed at https://huggingface.co/datasets/ChemFM/MolLangBench and https://github.com/TheLuoFengLab/MolLangBench, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2505_15054
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MolLangBench: A Comprehensive Benchmark for Language-Prompted Molecular Structure Recognition, Editing, and Generation
Cai, Feiyang
Bai, Jiahui
Tang, Tao
He, Guijuan
Luo, Joshua
Zhu, Tianyu
Pilla, Srikanth
Li, Gang
Liu, Ling
Luo, Feng
Computation and Language
Artificial Intelligence
Machine Learning
Biomolecules
Precise recognition, editing, and generation of molecules are essential prerequisites for both chemists and AI systems tackling various chemical tasks. We present MolLangBench, a comprehensive benchmark designed to evaluate fundamental molecule-language interface tasks: language-prompted molecular structure recognition, editing, and generation. To ensure high-quality, unambiguous, and deterministic outputs, we construct the recognition tasks using automated cheminformatics tools, and curate editing and generation tasks through rigorous expert annotation and validation. MolLangBench supports the evaluation of models that interface language with different molecular representations, including linear strings, molecular images, and molecular graphs. Evaluations of state-of-the-art models reveal significant limitations: the strongest model (GPT-5) achieves $86.2\%$ and $85.5\%$ accuracy on recognition and editing tasks, which are intuitively simple for humans, and performs even worse on the generation task, reaching only $43.0\%$ accuracy. These results highlight the shortcomings of current AI systems in handling even preliminary molecular recognition and manipulation tasks. We hope MolLangBench will catalyze further research toward more effective and reliable AI systems for chemical applications.The dataset and code can be accessed at https://huggingface.co/datasets/ChemFM/MolLangBench and https://github.com/TheLuoFengLab/MolLangBench, respectively.
title MolLangBench: A Comprehensive Benchmark for Language-Prompted Molecular Structure Recognition, Editing, and Generation
topic Computation and Language
Artificial Intelligence
Machine Learning
Biomolecules
url https://arxiv.org/abs/2505.15054