@inproceedings{liu-etal-2026-grounding,
title = "Grounding Structure in Language: Enriching Symbolic Representations for Molecular Reasoning",
author = "Liu, Zhengyuan and
He, Dan and
Chen, Nancy F. and
Wang, Wenya",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.819/",
pages = "17362--17382",
ISBN = "979-8-89176-462-0",
abstract = "Large language models (LLMs) show promise for scientific applications but struggle when domain knowledge is encoded in complex structures. Chemistry exemplifies this challenge: molecular structures encode rich relational data that dictates chemical meaning, yet standard formats like SMILES obscure this through arbitrary linearization. In this work, we systematically characterize which structural information lost during linearization most severely hampers LLM reasoning, decomposing the problem into IUPAC-grounded dimensions: substituent positions (locants), attachment points (anchoring), and modification constraints (valency). Our diagnostic reveals non-uniform failures across dimensions, with locant identification being especially challenging. We directly address the failures by grounding the linearized representations in structural context with each component targeting its corresponding diagnostic dimension. General-purpose LLMs with explicit grounding can outperform chemistry-specialized models on structure-aware molecule manipulation, suggesting structural context can compensate for domain-specific training. Moreover, we investigate a training-free inductive protocol that nearly doubles the accuracy of weaker models. These results point toward explicit structural grounding as a principled path to more reliable molecular reasoning across model scales."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-grounding">
<titleInfo>
<title>Grounding Structure in Language: Enriching Symbolic Representations for Molecular Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhengyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenya</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Large language models (LLMs) show promise for scientific applications but struggle when domain knowledge is encoded in complex structures. Chemistry exemplifies this challenge: molecular structures encode rich relational data that dictates chemical meaning, yet standard formats like SMILES obscure this through arbitrary linearization. In this work, we systematically characterize which structural information lost during linearization most severely hampers LLM reasoning, decomposing the problem into IUPAC-grounded dimensions: substituent positions (locants), attachment points (anchoring), and modification constraints (valency). Our diagnostic reveals non-uniform failures across dimensions, with locant identification being especially challenging. We directly address the failures by grounding the linearized representations in structural context with each component targeting its corresponding diagnostic dimension. General-purpose LLMs with explicit grounding can outperform chemistry-specialized models on structure-aware molecule manipulation, suggesting structural context can compensate for domain-specific training. Moreover, we investigate a training-free inductive protocol that nearly doubles the accuracy of weaker models. These results point toward explicit structural grounding as a principled path to more reliable molecular reasoning across model scales.</abstract>
<identifier type="citekey">liu-etal-2026-grounding</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.819/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>17362</start>
<end>17382</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Grounding Structure in Language: Enriching Symbolic Representations for Molecular Reasoning
%A Liu, Zhengyuan
%A He, Dan
%A Chen, Nancy F.
%A Wang, Wenya
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F liu-etal-2026-grounding
%X Large language models (LLMs) show promise for scientific applications but struggle when domain knowledge is encoded in complex structures. Chemistry exemplifies this challenge: molecular structures encode rich relational data that dictates chemical meaning, yet standard formats like SMILES obscure this through arbitrary linearization. In this work, we systematically characterize which structural information lost during linearization most severely hampers LLM reasoning, decomposing the problem into IUPAC-grounded dimensions: substituent positions (locants), attachment points (anchoring), and modification constraints (valency). Our diagnostic reveals non-uniform failures across dimensions, with locant identification being especially challenging. We directly address the failures by grounding the linearized representations in structural context with each component targeting its corresponding diagnostic dimension. General-purpose LLMs with explicit grounding can outperform chemistry-specialized models on structure-aware molecule manipulation, suggesting structural context can compensate for domain-specific training. Moreover, we investigate a training-free inductive protocol that nearly doubles the accuracy of weaker models. These results point toward explicit structural grounding as a principled path to more reliable molecular reasoning across model scales.
%U https://aclanthology.org/2026.findings-emnlp.819/
%P 17362-17382
Markdown (Informal)
[Grounding Structure in Language: Enriching Symbolic Representations for Molecular Reasoning](https://aclanthology.org/2026.findings-emnlp.819/) (Liu et al., Findings 2026)
ACL