@inproceedings{dey-etal-2025-gellm3o,
title = "{GeLLM{\textthreesuperior}O}: Generalizing Large Language Models for Multi-property Molecule Optimization",
author = "Dey, Vishal and
Hu, Xiao and
Ning, Xia",
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.1225/",
doi = "10.18653/v1/2025.acl-long.1225",
pages = "25192--25221",
ISBN = "979-8-89176-251-0",
abstract = "Despite recent advancements, most computational methods for molecule optimization are constrained to single- or double-property optimization tasks and suffer from poor scalability and generalizability to novel optimization tasks. Meanwhile, Large Language Models (LLMs) demonstrate remarkable out-of-domain generalizability to novel tasks. To demonstrate LLMs' potential for molecule optimization, we introduce \textbf{MuMOInstruct}, the first high-quality instruction-tuning dataset specifically focused on multi-property molecule optimization tasks. Leveraging \textbf{MuMOInstruct}, we develop \textbf{GeLLM{\textthreesuperior}O}s, a series of instruction-tuned LLMs for molecule optimization. Extensive evaluations across 5 in-domain and 5 out-of-domain tasks demonstrate that \textbf{GeLLM{\textthreesuperior}O}s consistently outperform state-of-the-art baselines. \textbf{GeLLM{\textthreesuperior}O}s also exhibit outstanding zero-shot generalization to unseen tasks, significantly outperforming powerful closed-source LLMs. Such strong generalizability demonstrates the tremendous potential of \textbf{GeLLM{\textthreesuperior}O}s as foundational models for molecule optimization, thereby tackling novel optimization tasks without resource-intensive retraining. \textbf{MuMOInstruct} and code are accessible through \url{https://github.com/ninglab/GeLLMO}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dey-etal-2025-gellm3o">
<titleInfo>
<title>GeLLM³O: Generalizing Large Language Models for Multi-property Molecule Optimization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vishal</namePart>
<namePart type="family">Dey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xia</namePart>
<namePart type="family">Ning</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Despite recent advancements, most computational methods for molecule optimization are constrained to single- or double-property optimization tasks and suffer from poor scalability and generalizability to novel optimization tasks. Meanwhile, Large Language Models (LLMs) demonstrate remarkable out-of-domain generalizability to novel tasks. To demonstrate LLMs’ potential for molecule optimization, we introduce MuMOInstruct, the first high-quality instruction-tuning dataset specifically focused on multi-property molecule optimization tasks. Leveraging MuMOInstruct, we develop GeLLM³Os, a series of instruction-tuned LLMs for molecule optimization. Extensive evaluations across 5 in-domain and 5 out-of-domain tasks demonstrate that GeLLM³Os consistently outperform state-of-the-art baselines. GeLLM³Os also exhibit outstanding zero-shot generalization to unseen tasks, significantly outperforming powerful closed-source LLMs. Such strong generalizability demonstrates the tremendous potential of GeLLM³Os as foundational models for molecule optimization, thereby tackling novel optimization tasks without resource-intensive retraining. MuMOInstruct and code are accessible through https://github.com/ninglab/GeLLMO.</abstract>
<identifier type="citekey">dey-etal-2025-gellm3o</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.1225</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.1225/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>25192</start>
<end>25221</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GeLLM³O: Generalizing Large Language Models for Multi-property Molecule Optimization
%A Dey, Vishal
%A Hu, Xiao
%A Ning, Xia
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F dey-etal-2025-gellm3o
%X Despite recent advancements, most computational methods for molecule optimization are constrained to single- or double-property optimization tasks and suffer from poor scalability and generalizability to novel optimization tasks. Meanwhile, Large Language Models (LLMs) demonstrate remarkable out-of-domain generalizability to novel tasks. To demonstrate LLMs’ potential for molecule optimization, we introduce MuMOInstruct, the first high-quality instruction-tuning dataset specifically focused on multi-property molecule optimization tasks. Leveraging MuMOInstruct, we develop GeLLM³Os, a series of instruction-tuned LLMs for molecule optimization. Extensive evaluations across 5 in-domain and 5 out-of-domain tasks demonstrate that GeLLM³Os consistently outperform state-of-the-art baselines. GeLLM³Os also exhibit outstanding zero-shot generalization to unseen tasks, significantly outperforming powerful closed-source LLMs. Such strong generalizability demonstrates the tremendous potential of GeLLM³Os as foundational models for molecule optimization, thereby tackling novel optimization tasks without resource-intensive retraining. MuMOInstruct and code are accessible through https://github.com/ninglab/GeLLMO.
%R 10.18653/v1/2025.acl-long.1225
%U https://aclanthology.org/2025.acl-long.1225/
%U https://doi.org/10.18653/v1/2025.acl-long.1225
%P 25192-25221
Markdown (Informal)
[GeLLM³O: Generalizing Large Language Models for Multi-property Molecule Optimization](https://aclanthology.org/2025.acl-long.1225/) (Dey et al., ACL 2025)
ACL