AutoRE: Document-Level Relation Extraction with Large Language Models

TL;DR

AutoRE is a novel document-level relation extraction model using large language models, introducing the RHF paradigm and PEFT fine-tuning, achieving state-of-the-art results on the RE-DocRED dataset.

Contribution

The paper presents AutoRE, an end-to-end DocRE model that employs a new RHF extraction paradigm and PEFT fine-tuning, addressing limitations of existing methods and improving performance.

Findings

Achieves state-of-the-art results on RE-DocRED dataset.

Surpasses previous methods by over 10% on dev and test sets.

Demonstrates effectiveness of RHF paradigm and PEFT in DocRE.

Abstract

Large Language Models (LLMs) have demonstrated exceptional abilities in comprehending and generating text, motivating numerous researchers to utilize them for Information Extraction (IE) purposes, including Relation Extraction (RE). Nonetheless, most existing methods are predominantly designed for Sentence-level Relation Extraction (SentRE) tasks, which typically encompass a restricted set of relations and triplet facts within a single sentence. Furthermore, certain approaches resort to treating relations as candidate choices integrated into prompt templates, leading to inefficient processing and suboptimal performance when tackling Document-Level Relation Extraction (DocRE) tasks, which entail handling multiple relations and triplet facts distributed across a given document, posing distinct challenges. To overcome these limitations, we introduce AutoRE, an end-to-end DocRE model that adopts a novel RE extraction paradigm named RHF (Relation-Head-Facts). Unlike existing approaches, AutoRE does not rely on the assumption of known relation options, making it more reflective of real-world scenarios. Additionally, we have developed an easily extensible RE framework using a Parameters Efficient Fine Tuning (PEFT) algorithm (QLoRA). Our experiments on the RE-DocRED dataset showcase AutoRE's best performance, achieving state-of-the-art results, surpassing TAG by 10.03\% and 9.03\% respectively on the dev and test set. The code is available at https://github.com/THUDM/AutoRE and the demonstration video is provided at https://www.youtube.com/watch?v=IhKRsZUAxKk.