LLM With Relation Classifier for Document-Level Relation Extraction

doi:10.1109/tbdata.2026.3668580

LLM With Relation Classifier for Document-Level Relation Extraction

2026-08-01

2

PRE

AI

DOI：10.1109/tbdata.2026.3668580

Original

Original request for help

Save

Abstract

En 中文

Large language models (LLMs) have created a new paradigm for natural language processing. Despite their advancement, LLM-based methods still lag behind traditional approaches in document-level relation extraction (DocRE), a critical task for understanding complex entity relations within long context. This paper investigates the causes of this performance gap, identifying the dispersion of attention by LLMs due to entity pairs without relations as a key factor. We then introduce a novel classifier-LLM approach to DocRE. Particularly, the proposed approach begins with a classifier designed to select entity pair candidates that exhibit potential relations and then feed them to LLM for final relation classification. This method ensures that the LLM's attention is directed at relation-expressing entity pairs instead of those without relations during inference. Experiments on DocRE benchmarks reveal that our method significantly outperforms recent LLM-based DocRE models and narrows the performance gap with state-of-the-art BERT-based models.

Keywords:

Big Data

Proposals

Transformers

Semantics

Cognition

Benchmark testing

Attention mechanisms

Adaptation models

Nickel

Large language models

Document-level relation extraction (DocRE)

attention mechanism

large language models (LLMs)

in-context learning

LLM With Relation Classifier for Document-Level Relation Extraction

Abstract

Journal

Organization

Cited Papers