ACL Findings2026
HCRE: LLM-based Hierarchical Classification for Cross-Document Relation Extraction with a Prediction-then-Verification Strategy
Guoqi Ma, Liang Zhang, Hongyao Tu, Hao Fu, Hui Li, Yujie Lin, Longyue Wang, Weihua Luo, Jinsong Su
Abstract
Cross-document relation extraction (RE) aimsto identify relations between the head and tail entities located in different documents.Existing approaches typically adopt the paradigm of "Small Language Model (SLM) + Classifier".However, the limited language understanding ability of SLMs hinders further improvement of their performance.In this paper, we conduct a preliminary study to explore the performance of Large Language Models (LLMs) in crossdocument RE.Despite their extensive parameters, our findings indicate that LLMs do not consistently surpass existing SLMs.Further analysis suggests that the underperformance is largely attributed to the challenges posed by the numerous predefined relations.To overcome this issue, we propose an LLM-based Hierarchical Classification model for crossdocument RE (HCRE), which consists of two core components: 1) an LLM for relation prediction and 2) a hierarchical relation tree derived from the predefined relation set.This tree enables the LLM to perform hierarchical classification, where the target relation is inferred level by level.Since the number of child nodes is much smaller than the size of the entire predefined relation set, the hierarchical relation tree significantly reduces the number of relation options that LLM needs to consider during inference.However, hierarchical classification introduces the risk of error propagation across levels.To mitigate this, we propose a prediction-then-verification inference strategy that improves prediction reliability through multi-view verification at each level.Extensive experiments show that HCRE outperforms existing baselines, validating its effectiveness.We release our code at https: //github.com/XMUDeepLIT/HCRE.
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.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers1
Builds on24
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- Revisiting Relation Extraction in the era of Large Language ModelsSomin Wadhwa, Silvio Amir, Byron C. WallaceACL 2023 · 145 citations
- Reasoning with Language Model is Planning with World ModelShibo Hao, Yi Gu, Haodi Ma, Joshua Jiahua Hong et al.EMNLP 2023 · 109 citations
- TELEClass: Taxonomy Enrichment and LLM-Enhanced Hierarchical Text Classification with Minimal SupervisionYunyi Zhang, Ruozhen Yang, Xueqiang Xu, Rui Li et al.WWW 2025 · 53 citations
- Entity-centered Cross-document Relation ExtractionFengqi Wang, Fei Li, Hao Fei, Jingye Li et al.EMNLP 2022 · 49 citations
Related papers
- LLM-OREF: An Open Relation Extraction Framework Based on Large Language ModelsHongyao Tu, Liang Zhang, Yujie Lin, Xin Lin et al.EMNLP 2025 · 2 citations
- Knowledge-Driven Cross-Document Relation ExtractionMonika Jain, Raghava Mutharaju, Kuldeep Singh, Ramakanth KavuluruACL Findings 2024 · 5 citations
- 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
- Towards Better Document-level Relation Extraction via Iterative InferenceLiang Zhang, Jinsong Su, Yidong Chen, Zhongjian Miao et al.EMNLP 2022 · 11 citations
- Revisiting Document-Level Relation Extraction with Context-Guided Link PredictionMonika Jain, Raghava Mutharaju, Ramakanth Kavuluru, Kuldeep SinghAAAI 2024 · 17 citations
