# HCRE: LLM-based Hierarchical Classification for Cross-Document Relation Extraction with a Prediction-then-Verification Strategy

arXiv: https://arxiv.org/abs/2604.07937 · HTML: https://mlsanity.com/paper/2604.07937/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 40 references that are in the map.
- First posted on arXiv 9 Apr 2026.

## Builds on (most cited first, 20 of 20)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [DocRED: A Large-Scale Document-Level Relation Extraction Dataset](https://mlsanity.com/paper/1906.06127/) (2019)
- [InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction](https://mlsanity.com/paper/2304.08085/) (2023)
- [Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting](https://mlsanity.com/paper/2407.08223/) (2024)
- [CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors](https://mlsanity.com/paper/2305.05711/) (2023)
- [TELEClass: Taxonomy Enrichment and LLM-Enhanced Hierarchical Text Classification with Minimal Supervision](https://mlsanity.com/paper/2403.00165/) (2024)
- [Entity-centered Cross-document Relation Extraction](https://mlsanity.com/paper/2210.16541/) (2022)
- [Retrieval-style In-Context Learning for Few-shot Hierarchical Text Classification](https://mlsanity.com/paper/2406.17534/) (2024)
- [Constrained Sequence-to-Tree Generation for Hierarchical Text Classification](https://mlsanity.com/paper/2204.00811/) (2022)
- [Multi-hop Evidence Retrieval for Cross-document Relation Extraction](https://mlsanity.com/paper/2212.10786/) (2022)
- [Can Large Language Models Serve as Effective Classifiers for Hierarchical Multi-Label Classification of Scientific Documents at Industrial Scale?](https://mlsanity.com/paper/2412.05137/) (2024)
- [Grasping the Essentials: Tailoring Large Language Models for Zero-Shot Relation Extraction](https://mlsanity.com/paper/2402.11142/) (2024)
- [Towards Better Document-level Relation Extraction via Iterative Inference](https://mlsanity.com/paper/2211.14470/) (2022)
- [HiGen: Hierarchy-Aware Sequence Generation for Hierarchical Text Classification](https://mlsanity.com/paper/2402.01696/) (2024)
- [Towards Better Graph-based Cross-document Relation Extraction via Non-bridge Entity Enhancement and Prediction Debiasing](https://mlsanity.com/paper/2406.16529/) (2024)
- [One2set + Large Language Model: Best Partners for Keyphrase Generation](https://mlsanity.com/paper/2410.03421/) (2024)
- [Knowledge-Driven Cross-Document Relation Extraction](https://mlsanity.com/paper/2405.13546/) (2024)
- [Reward-based Input Construction for Cross-document Relation Extraction](https://mlsanity.com/paper/2405.20649/) (2024)

## Built on by (most cited first, 2 of 2)

- [SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context](https://mlsanity.com/paper/2604.11716/) (2026)
- [ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models](https://mlsanity.com/paper/2605.18879/) (2026)

## Abstract (arXiv)

Cross-document relation extraction (RE) aims to identify relations between the head and tail entities located in different documents. Existing approaches typically adopt the paradigm of ``textitSmall 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 cross-document 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 underlineHierarchical underlineClassification model for cross-document underlineRE (HCRE), which consists of two core components: 1) an LLM for relation prediction and 2) a textithierarchical 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 textitprediction-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.