ACL Findings2025
GLiM: Integrating Graph Transformer and LLM for Document-Level Biomedical Relation Extraction with Incomplete Labeling
Hao Fang, Yuejie Zhang, Rui Feng, Yingwen Wang, Qing Wang, Wen He, Xiaobo Zhang, Tao Zhang, Shang Gao
Abstract
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 graphenhanced Transformers with LLM inference for biomedical DocRE. Code will be released at https://github.com/HaoFang10/GLiM.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on11
- Document-Level Relation Extraction with Adaptive Thresholding and Localized Context PoolingWenxuan Zhou, Kevin Huang, Tengyu Ma, Jing HuangAAAI 2021 · 360 citations
- Pure Transformers are Powerful Graph LearnersJinwoo Kim, Dat Nguyen, Seonwoo Min, Sungjun Cho et al.NeurIPS 2022 · 311 citations
- Revisiting Relation Extraction in the era of Large Language ModelsSomin Wadhwa, Silvio Amir, Byron C. WallaceACL 2023 · 145 citations
- Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge DistillationQingyu Tan, Ruidan He, Lidong Bing, Hwee Tou NgACL Findings 2022 · 136 citations
- GPT-RE: In-context Learning for Relation Extraction using Large Language ModelsZhen Wan, Fei Cheng, Zhuoyuan Mao, Qianying Liu et al.EMNLP 2023 · 132 citations
Related papers
- Enhanced Reasoning for Biomedical Document-Level Relation Extraction via a Novel Cascade Language Model FrameworkHaohua Song, Wenhao Gu, Zhijing Li, Yunwen Yu et al.ACL 2026
- Document-Level Relation Extraction with Global Relations and Entity Pair ReasoningFu Zhang, Yi Yan, Jingwei ChengACL Findings 2025 · 2 citations
- Latent Relation Language ModelsHiroaki Hayashi, Zecong Hu, Chenyan Xiong, Graham NeubigAAAI 2020 · 43 citations
- DyNAS-DDI: Dynamic Pairwise Architecture Search for Generalizable Drug-Drug Interaction LLMLinxin Xiao, Xin Wang, Zeyang Zhang, Yang Yao et al.ACM MM 2025 · 1 citation
- Temporal Relation Extraction in Clinical Texts: A Span-based Graph Transformer ApproachRochana Chaturvedi, Peyman Baghershahi, Sourav Medya, Barbara Di EugenioACL 2025
