@inproceedings{wang-etal-2026-survey,
title = "A Survey of Large Language Models for Text-Guided Molecular Discovery: From Molecule Generation to Optimization",
author = "Wang, Ziqing and
Zhang, Kexin and
Zhao, Zihan and
Wen, Yibo and
Pandey, Abhishek and
Liu, Han and
Ding, Kaize",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.2026/",
pages = "43738--43769",
ISBN = "979-8-89176-390-6",
abstract = "Large language models (LLMs) are introducing a paradigm shift in molecular discovery by enabling text-guided interaction with chemical spaces through natural language and symbolic notations, with emerging extensions to incorporate multi-modal inputs. To advance this emerging field, this survey provides an up-to-date and forward-looking review of the emerging use of LLMs for two central tasks: molecule generation and molecule optimization. We organize our survey around four fundamental challenges that have emerged as critical evaluation dimensions in recent studies: ensuring validity, enhancing synthesizability, achieving precise property control, and maximizing diversity. Based on this, we systematically analyze how current LLM learning paradigms are applied to tackle each challenge, revealing the distinct capabilities and inherent limitations of each approach. In addition, we include the commonly used datasets and evaluation protocols aligned with these challenges. We conclude by discussing future directions, positioning this survey as a resource for researchers working at the intersection of LLMs and molecular science. A continuously updated reading list is available at \url{https://github.com/REAL-Lab-NU/Awesome-LLM-Centric-Molecular-Discovery}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-survey">
<titleInfo>
<title>A Survey of Large Language Models for Text-Guided Molecular Discovery: From Molecule Generation to Optimization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ziqing</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kexin</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zihan</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yibo</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhishek</namePart>
<namePart type="family">Pandey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Han</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaize</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Large language models (LLMs) are introducing a paradigm shift in molecular discovery by enabling text-guided interaction with chemical spaces through natural language and symbolic notations, with emerging extensions to incorporate multi-modal inputs. To advance this emerging field, this survey provides an up-to-date and forward-looking review of the emerging use of LLMs for two central tasks: molecule generation and molecule optimization. We organize our survey around four fundamental challenges that have emerged as critical evaluation dimensions in recent studies: ensuring validity, enhancing synthesizability, achieving precise property control, and maximizing diversity. Based on this, we systematically analyze how current LLM learning paradigms are applied to tackle each challenge, revealing the distinct capabilities and inherent limitations of each approach. In addition, we include the commonly used datasets and evaluation protocols aligned with these challenges. We conclude by discussing future directions, positioning this survey as a resource for researchers working at the intersection of LLMs and molecular science. A continuously updated reading list is available at https://github.com/REAL-Lab-NU/Awesome-LLM-Centric-Molecular-Discovery.</abstract>
<identifier type="citekey">wang-etal-2026-survey</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.2026/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>43738</start>
<end>43769</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Survey of Large Language Models for Text-Guided Molecular Discovery: From Molecule Generation to Optimization
%A Wang, Ziqing
%A Zhang, Kexin
%A Zhao, Zihan
%A Wen, Yibo
%A Pandey, Abhishek
%A Liu, Han
%A Ding, Kaize
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F wang-etal-2026-survey
%X Large language models (LLMs) are introducing a paradigm shift in molecular discovery by enabling text-guided interaction with chemical spaces through natural language and symbolic notations, with emerging extensions to incorporate multi-modal inputs. To advance this emerging field, this survey provides an up-to-date and forward-looking review of the emerging use of LLMs for two central tasks: molecule generation and molecule optimization. We organize our survey around four fundamental challenges that have emerged as critical evaluation dimensions in recent studies: ensuring validity, enhancing synthesizability, achieving precise property control, and maximizing diversity. Based on this, we systematically analyze how current LLM learning paradigms are applied to tackle each challenge, revealing the distinct capabilities and inherent limitations of each approach. In addition, we include the commonly used datasets and evaluation protocols aligned with these challenges. We conclude by discussing future directions, positioning this survey as a resource for researchers working at the intersection of LLMs and molecular science. A continuously updated reading list is available at https://github.com/REAL-Lab-NU/Awesome-LLM-Centric-Molecular-Discovery.
%U https://aclanthology.org/2026.acl-long.2026/
%P 43738-43769
Markdown (Informal)
[A Survey of Large Language Models for Text-Guided Molecular Discovery: From Molecule Generation to Optimization](https://aclanthology.org/2026.acl-long.2026/) (Wang et al., ACL 2026)
ACL
- Ziqing Wang, Kexin Zhang, Zihan Zhao, Yibo Wen, Abhishek Pandey, Han Liu, and Kaize Ding. 2026. A Survey of Large Language Models for Text-Guided Molecular Discovery: From Molecule Generation to Optimization. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 43738–43769, San Diego, California, United States. Association for Computational Linguistics.