@inproceedings{li-etal-2026-gla,
title = "{GLA}: Grounding Large Language Models in Molecular Hierarchy for Chemical Understanding",
author = "Li, Yingxu and
Zeng, Jingjie and
Wang, Zekun and
Lin, Hongfei and
Yang, Liang",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1515/",
pages = "30311--30323",
ISBN = "979-8-89176-395-1",
abstract = "Conventional Euclidean geometries lead to structural distortion and entangle core pharmacophoric identities with peripheral groups. Existing molecule-language models, relying on linear or uniform encodings, often obscure the hierarchical organization of chemical semantics. To address this, we propose Geometric-Language Alignment (GLA), a framework integrating intrinsic molecular topology into large language models. GLA employs a mixed-curvature encoder that adaptively learns geometric representations through a gating mechanism. These representations are aligned with text via a dual-view contrastive objective and injected into a frozen language model. Experiments on cross-modal retrieval, captioning, and property prediction benchmarks show GLA consistently improves performance over baselines, suggesting that modeling geometric heterogeneity enhances the grounding between molecular structure and chemical language."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-gla">
<titleInfo>
<title>GLA: Grounding Large Language Models in Molecular Hierarchy for Chemical Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yingxu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingjie</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zekun</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongfei</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Yang</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>Findings of the Association for Computational Linguistics: ACL 2026</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">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Conventional Euclidean geometries lead to structural distortion and entangle core pharmacophoric identities with peripheral groups. Existing molecule-language models, relying on linear or uniform encodings, often obscure the hierarchical organization of chemical semantics. To address this, we propose Geometric-Language Alignment (GLA), a framework integrating intrinsic molecular topology into large language models. GLA employs a mixed-curvature encoder that adaptively learns geometric representations through a gating mechanism. These representations are aligned with text via a dual-view contrastive objective and injected into a frozen language model. Experiments on cross-modal retrieval, captioning, and property prediction benchmarks show GLA consistently improves performance over baselines, suggesting that modeling geometric heterogeneity enhances the grounding between molecular structure and chemical language.</abstract>
<identifier type="citekey">li-etal-2026-gla</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1515/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>30311</start>
<end>30323</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GLA: Grounding Large Language Models in Molecular Hierarchy for Chemical Understanding
%A Li, Yingxu
%A Zeng, Jingjie
%A Wang, Zekun
%A Lin, Hongfei
%A Yang, Liang
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F li-etal-2026-gla
%X Conventional Euclidean geometries lead to structural distortion and entangle core pharmacophoric identities with peripheral groups. Existing molecule-language models, relying on linear or uniform encodings, often obscure the hierarchical organization of chemical semantics. To address this, we propose Geometric-Language Alignment (GLA), a framework integrating intrinsic molecular topology into large language models. GLA employs a mixed-curvature encoder that adaptively learns geometric representations through a gating mechanism. These representations are aligned with text via a dual-view contrastive objective and injected into a frozen language model. Experiments on cross-modal retrieval, captioning, and property prediction benchmarks show GLA consistently improves performance over baselines, suggesting that modeling geometric heterogeneity enhances the grounding between molecular structure and chemical language.
%U https://aclanthology.org/2026.findings-acl.1515/
%P 30311-30323
Markdown (Informal)
[GLA: Grounding Large Language Models in Molecular Hierarchy for Chemical Understanding](https://aclanthology.org/2026.findings-acl.1515/) (Li et al., Findings 2026)
ACL