@inproceedings{fang-etal-2025-glim,
title = "{GL}i{M}: Integrating Graph Transformer and {LLM} for Document-Level Biomedical Relation Extraction with Incomplete Labeling",
author = "Fang, Hao and
Zhang, Yuejie and
Feng, Rui and
Wang, Yingwen and
Wang, Qing and
He, Wen and
Zhang, Xiaobo and
Zhang, Tao and
Gao, Shang",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.727/",
doi = "10.18653/v1/2025.findings-acl.727",
pages = "14131--14146",
ISBN = "979-8-89176-256-5",
abstract = "Document-level relation extraction (DocRE) identifies relations between entities across an entire document. However, as the number and complexity of entities and entity-pair relations grow, the problem space expands quadratically, causing incomplete annotations and frequent false negatives, especially in biomedical datasets due to high construction costs. This leads to low recall in real-world scenarios. To address this, we propose GLiM, a novel framework that reduces the problem space using a graph-enhanced Transformer-based model and leverages large language models (LLMs) for reasoning. GLiM employs a cascaded approach: first, a graph-enhanced Transformer processes entity-pair relations with finer granularity by dynamically adjusting the graph size based on the number of entities; then, LLM inference handles challenging cases. Experiments show that GLiM boosts average recall and F1 scores by +6.34 and +4.41, respectively, outperforming state-of-the-art models on biomedical benchmarks. These results demonstrate the effectiveness of combining graph-enhanced Transformers with LLM inference for biomedical DocRE. Code will be released at https://github.com/HaoFang10/GLiM."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fang-etal-2025-glim">
<titleInfo>
<title>GLiM: Integrating Graph Transformer and LLM for Document-Level Biomedical Relation Extraction with Incomplete Labeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuejie</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingwen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qing</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wen</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaobo</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shang</namePart>
<namePart type="family">Gao</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>Findings of the Association for Computational Linguistics: ACL 2025</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">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Document-level relation extraction (DocRE) identifies relations between entities across an entire document. However, as the number and complexity of entities and entity-pair relations grow, the problem space expands quadratically, causing incomplete annotations and frequent false negatives, especially in biomedical datasets due to high construction costs. This leads to low recall in real-world scenarios. To address this, we propose GLiM, a novel framework that reduces the problem space using a graph-enhanced Transformer-based model and leverages large language models (LLMs) for reasoning. GLiM employs a cascaded approach: first, a graph-enhanced Transformer processes entity-pair relations with finer granularity by dynamically adjusting the graph size based on the number of entities; then, LLM inference handles challenging cases. Experiments show that GLiM boosts average recall and F1 scores by +6.34 and +4.41, respectively, outperforming state-of-the-art models on biomedical benchmarks. These results demonstrate the effectiveness of combining graph-enhanced Transformers with LLM inference for biomedical DocRE. Code will be released at https://github.com/HaoFang10/GLiM.</abstract>
<identifier type="citekey">fang-etal-2025-glim</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.727</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.727/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>14131</start>
<end>14146</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GLiM: Integrating Graph Transformer and LLM for Document-Level Biomedical Relation Extraction with Incomplete Labeling
%A Fang, Hao
%A Zhang, Yuejie
%A Feng, Rui
%A Wang, Yingwen
%A Wang, Qing
%A He, Wen
%A Zhang, Xiaobo
%A Zhang, Tao
%A Gao, Shang
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F fang-etal-2025-glim
%X Document-level relation extraction (DocRE) identifies relations between entities across an entire document. However, as the number and complexity of entities and entity-pair relations grow, the problem space expands quadratically, causing incomplete annotations and frequent false negatives, especially in biomedical datasets due to high construction costs. This leads to low recall in real-world scenarios. To address this, we propose GLiM, a novel framework that reduces the problem space using a graph-enhanced Transformer-based model and leverages large language models (LLMs) for reasoning. GLiM employs a cascaded approach: first, a graph-enhanced Transformer processes entity-pair relations with finer granularity by dynamically adjusting the graph size based on the number of entities; then, LLM inference handles challenging cases. Experiments show that GLiM boosts average recall and F1 scores by +6.34 and +4.41, respectively, outperforming state-of-the-art models on biomedical benchmarks. These results demonstrate the effectiveness of combining graph-enhanced Transformers with LLM inference for biomedical DocRE. Code will be released at https://github.com/HaoFang10/GLiM.
%R 10.18653/v1/2025.findings-acl.727
%U https://aclanthology.org/2025.findings-acl.727/
%U https://doi.org/10.18653/v1/2025.findings-acl.727
%P 14131-14146
Markdown (Informal)
[GLiM: Integrating Graph Transformer and LLM for Document-Level Biomedical Relation Extraction with Incomplete Labeling](https://aclanthology.org/2025.findings-acl.727/) (Fang et al., Findings 2025)
ACL
- Hao Fang, Yuejie Zhang, Rui Feng, Yingwen Wang, Qing Wang, Wen He, Xiaobo Zhang, Tao Zhang, and Shang Gao. 2025. GLiM: Integrating Graph Transformer and LLM for Document-Level Biomedical Relation Extraction with Incomplete Labeling. In Findings of the Association for Computational Linguistics: ACL 2025, pages 14131–14146, Vienna, Austria. Association for Computational Linguistics.