@inproceedings{zhang-etal-2026-cite,
title = "{CITE}: Benchmarking Heterogeneous Text-Attributed Graph Models",
author = "Zhang, Chenghao and
Long, Qingqing and
Wang, Ludi and
Cui, Wenjuan and
Yu, Jianjun and
Du, Yi",
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.1449/",
pages = "31426--31448",
ISBN = "979-8-89176-390-6",
abstract = "Recent advances in large language models (LLMs) and text-aware graph learning have increased interest in reasoning over text-attributed graphs(TAGs). In many real-world settings, such graphs are inherently heterogeneous, with most existing benchmarks remaining largely homogeneous in structure. As a result, the lack of large-scale benchmarks for heterogeneous text-attributed graphs has hindered systematic evaluation and fair comparison of existing methods. In this work, we introduce CITE - **C**atalytic **I**nformation **T**extual **E**ntities Graph, the first and largest heterogeneous text-attributed citation graph benchmark for catalytic materials. CITE contains over 438K nodes and 1.2M edges spanning four node types and four relation types, with rich node-level textual information. We establish standardized evaluation protocols for node classification and link prediction, and conduct ablation studies to assess the impact of graph heterogeneity and textual attributes. Using CITE, we benchmark four classes of learning paradigms, including homogeneous graph models, heterogeneous graph models, LLM-centric models, and hybrid LLM{--}graph models. By providing a large-scale heterogeneous text-attributed benchmark together with standardized evaluation protocols and comprehensive baselines, CITE enables systematic assessment across diverse modeling paradigms and offers new insights into text-aware and LLM-enhanced graph learning. The dataset, codebase and evaluation suite are publicly available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-cite">
<titleInfo>
<title>CITE: Benchmarking Heterogeneous Text-Attributed Graph Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chenghao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingqing</namePart>
<namePart type="family">Long</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ludi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjuan</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianjun</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Du</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>Recent advances in large language models (LLMs) and text-aware graph learning have increased interest in reasoning over text-attributed graphs(TAGs). In many real-world settings, such graphs are inherently heterogeneous, with most existing benchmarks remaining largely homogeneous in structure. As a result, the lack of large-scale benchmarks for heterogeneous text-attributed graphs has hindered systematic evaluation and fair comparison of existing methods. In this work, we introduce CITE - **C**atalytic **I**nformation **T**extual **E**ntities Graph, the first and largest heterogeneous text-attributed citation graph benchmark for catalytic materials. CITE contains over 438K nodes and 1.2M edges spanning four node types and four relation types, with rich node-level textual information. We establish standardized evaluation protocols for node classification and link prediction, and conduct ablation studies to assess the impact of graph heterogeneity and textual attributes. Using CITE, we benchmark four classes of learning paradigms, including homogeneous graph models, heterogeneous graph models, LLM-centric models, and hybrid LLM–graph models. By providing a large-scale heterogeneous text-attributed benchmark together with standardized evaluation protocols and comprehensive baselines, CITE enables systematic assessment across diverse modeling paradigms and offers new insights into text-aware and LLM-enhanced graph learning. The dataset, codebase and evaluation suite are publicly available.</abstract>
<identifier type="citekey">zhang-etal-2026-cite</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1449/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>31426</start>
<end>31448</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CITE: Benchmarking Heterogeneous Text-Attributed Graph Models
%A Zhang, Chenghao
%A Long, Qingqing
%A Wang, Ludi
%A Cui, Wenjuan
%A Yu, Jianjun
%A Du, Yi
%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 zhang-etal-2026-cite
%X Recent advances in large language models (LLMs) and text-aware graph learning have increased interest in reasoning over text-attributed graphs(TAGs). In many real-world settings, such graphs are inherently heterogeneous, with most existing benchmarks remaining largely homogeneous in structure. As a result, the lack of large-scale benchmarks for heterogeneous text-attributed graphs has hindered systematic evaluation and fair comparison of existing methods. In this work, we introduce CITE - **C**atalytic **I**nformation **T**extual **E**ntities Graph, the first and largest heterogeneous text-attributed citation graph benchmark for catalytic materials. CITE contains over 438K nodes and 1.2M edges spanning four node types and four relation types, with rich node-level textual information. We establish standardized evaluation protocols for node classification and link prediction, and conduct ablation studies to assess the impact of graph heterogeneity and textual attributes. Using CITE, we benchmark four classes of learning paradigms, including homogeneous graph models, heterogeneous graph models, LLM-centric models, and hybrid LLM–graph models. By providing a large-scale heterogeneous text-attributed benchmark together with standardized evaluation protocols and comprehensive baselines, CITE enables systematic assessment across diverse modeling paradigms and offers new insights into text-aware and LLM-enhanced graph learning. The dataset, codebase and evaluation suite are publicly available.
%U https://aclanthology.org/2026.acl-long.1449/
%P 31426-31448
Markdown (Informal)
[CITE: Benchmarking Heterogeneous Text-Attributed Graph Models](https://aclanthology.org/2026.acl-long.1449/) (Zhang et al., ACL 2026)
ACL
- Chenghao Zhang, Qingqing Long, Ludi Wang, Wenjuan Cui, Jianjun Yu, and Yi Du. 2026. CITE: Benchmarking Heterogeneous Text-Attributed Graph Models. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 31426–31448, San Diego, California, United States. Association for Computational Linguistics.