@inproceedings{hu-2026-graph,
title = "Graph Evidence Is Not Text Evidence: Serialization Faithfulness as Structural Invariance in Graph-Grounded Language Models",
author = "Hu, Lifan",
editor = "Wang, Yimu and
Choi, Yee Man and
Wu, Di and
Ouyang, Siqi and
Azadani, Mozhgan Nasr and
Fung, Yi R. (May)",
booktitle = "Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently ({G}round{LM} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.groundlm-1.23/",
pages = "305--309",
ISBN = "979-8-89176-478-1",
abstract = "Graph-grounded language models are usually evaluated by answer accuracy, yet a serialized prompt is a string representation of a graph rather than the graph itself. We argue that faithful graph-grounded reasoning requires the composed predictor $F_\theta \circ z$ to be well-defined on graph-query equivalence classes: structurally equivalent graph-query pairs should induce the same prediction regardless of textual realization. We formalize this as a structural invariance property, decompose unfaithfulness into syntactic instability, semantic interference, and distractor susceptibility, and introduce corresponding diagnostics. On controlled graph reasoning tasks, DeepSeek-V4-Flash achieves 98.9{\%} accuracy and near-perfect syntactic stability ($FS = .975$), yet its isomorphism consistency drops from .969 to .701 under semantic-name relabeling ($∆_{sem} = .268$); only 72.9{\%} of originally correct answers survive this transformation. Across four model families, we observe targeted semantic interference in high-accuracy models, broad unfaithfulness in weaker models, and near-perfect invariance as a capability ceiling. A graph-grounded LLM can be accurate without being structurally faithful: its predictions may fail to remain invariant under graph-equivalent textual relabelings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hu-2026-graph">
<titleInfo>
<title>Graph Evidence Is Not Text Evidence: Serialization Faithfulness as Structural Invariance in Graph-Grounded Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lifan</namePart>
<namePart type="family">Hu</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>Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yimu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yee</namePart>
<namePart type="given">Man</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Di</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siqi</namePart>
<namePart type="family">Ouyang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mozhgan</namePart>
<namePart type="given">Nasr</namePart>
<namePart type="family">Azadani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="given">R</namePart>
<namePart type="given">(May)</namePart>
<namePart type="family">Fung</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">979-8-89176-478-1</identifier>
</relatedItem>
<abstract>Graph-grounded language models are usually evaluated by answer accuracy, yet a serialized prompt is a string representation of a graph rather than the graph itself. We argue that faithful graph-grounded reasoning requires the composed predictor F_θ \circ z to be well-defined on graph-query equivalence classes: structurally equivalent graph-query pairs should induce the same prediction regardless of textual realization. We formalize this as a structural invariance property, decompose unfaithfulness into syntactic instability, semantic interference, and distractor susceptibility, and introduce corresponding diagnostics. On controlled graph reasoning tasks, DeepSeek-V4-Flash achieves 98.9% accuracy and near-perfect syntactic stability (FS = .975), yet its isomorphism consistency drops from .969 to .701 under semantic-name relabeling (∆_sem = .268); only 72.9% of originally correct answers survive this transformation. Across four model families, we observe targeted semantic interference in high-accuracy models, broad unfaithfulness in weaker models, and near-perfect invariance as a capability ceiling. A graph-grounded LLM can be accurate without being structurally faithful: its predictions may fail to remain invariant under graph-equivalent textual relabelings.</abstract>
<identifier type="citekey">hu-2026-graph</identifier>
<location>
<url>https://aclanthology.org/2026.groundlm-1.23/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>305</start>
<end>309</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Graph Evidence Is Not Text Evidence: Serialization Faithfulness as Structural Invariance in Graph-Grounded Language Models
%A Hu, Lifan
%Y Wang, Yimu
%Y Choi, Yee Man
%Y Wu, Di
%Y Ouyang, Siqi
%Y Azadani, Mozhgan Nasr
%Y Fung, Yi R. (May)
%S Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-478-1
%F hu-2026-graph
%X Graph-grounded language models are usually evaluated by answer accuracy, yet a serialized prompt is a string representation of a graph rather than the graph itself. We argue that faithful graph-grounded reasoning requires the composed predictor F_θ \circ z to be well-defined on graph-query equivalence classes: structurally equivalent graph-query pairs should induce the same prediction regardless of textual realization. We formalize this as a structural invariance property, decompose unfaithfulness into syntactic instability, semantic interference, and distractor susceptibility, and introduce corresponding diagnostics. On controlled graph reasoning tasks, DeepSeek-V4-Flash achieves 98.9% accuracy and near-perfect syntactic stability (FS = .975), yet its isomorphism consistency drops from .969 to .701 under semantic-name relabeling (∆_sem = .268); only 72.9% of originally correct answers survive this transformation. Across four model families, we observe targeted semantic interference in high-accuracy models, broad unfaithfulness in weaker models, and near-perfect invariance as a capability ceiling. A graph-grounded LLM can be accurate without being structurally faithful: its predictions may fail to remain invariant under graph-equivalent textual relabelings.
%U https://aclanthology.org/2026.groundlm-1.23/
%P 305-309
Markdown (Informal)
[Graph Evidence Is Not Text Evidence: Serialization Faithfulness as Structural Invariance in Graph-Grounded Language Models](https://aclanthology.org/2026.groundlm-1.23/) (Hu, GroundLM 2026)
ACL