LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yu, Botao, Baker, Frazier N., Chen, Ziqi, Ning, Xia, Sun, Huan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916351877054464
author Yu, Botao
Baker, Frazier N.
Chen, Ziqi
Ning, Xia
Sun, Huan
author_facet Yu, Botao
Baker, Frazier N.
Chen, Ziqi
Ning, Xia
Sun, Huan
contents Chemistry plays a crucial role in many domains, such as drug discovery and material science. While large language models (LLMs) such as GPT-4 exhibit remarkable capabilities on natural language processing tasks, existing research indicates that their performance on chemistry tasks is discouragingly low. In this paper, however, we demonstrate that our developed LLMs can achieve very strong results on a comprehensive set of chemistry tasks, outperforming the most advanced GPT-4 and Claude 3 Opus by a substantial margin. To accomplish this, we propose SMolInstruct, a large-scale, comprehensive, and high-quality dataset for instruction tuning. It contains 14 selected chemistry tasks and over three million samples, laying a solid foundation for training and evaluating LLMs for chemistry. Using SMolInstruct, we fine-tune a set of open-source LLMs, among which, we find that Mistral serves as the best base model for chemistry tasks. Our analysis further demonstrates the critical role of the proposed dataset in driving the performance improvements.
format Preprint
id arxiv_https___arxiv_org_abs_2402_09391
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset
Yu, Botao
Baker, Frazier N.
Chen, Ziqi
Ning, Xia
Sun, Huan
Artificial Intelligence
Computational Engineering, Finance, and Science
Computation and Language
Chemistry plays a crucial role in many domains, such as drug discovery and material science. While large language models (LLMs) such as GPT-4 exhibit remarkable capabilities on natural language processing tasks, existing research indicates that their performance on chemistry tasks is discouragingly low. In this paper, however, we demonstrate that our developed LLMs can achieve very strong results on a comprehensive set of chemistry tasks, outperforming the most advanced GPT-4 and Claude 3 Opus by a substantial margin. To accomplish this, we propose SMolInstruct, a large-scale, comprehensive, and high-quality dataset for instruction tuning. It contains 14 selected chemistry tasks and over three million samples, laying a solid foundation for training and evaluating LLMs for chemistry. Using SMolInstruct, we fine-tune a set of open-source LLMs, among which, we find that Mistral serves as the best base model for chemistry tasks. Our analysis further demonstrates the critical role of the proposed dataset in driving the performance improvements.
title LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset
topic Artificial Intelligence
Computational Engineering, Finance, and Science
Computation and Language
url https://arxiv.org/abs/2402.09391