GenRES: Rethinking Evaluation for Generative Relation Extraction in the Era of Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Pengcheng, Lin, Jiacheng, Wang, Zifeng, Sun, Jimeng, Han, Jiawei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917591314857984
author Jiang, Pengcheng
Lin, Jiacheng
Wang, Zifeng
Sun, Jimeng
Han, Jiawei
author_facet Jiang, Pengcheng
Lin, Jiacheng
Wang, Zifeng
Sun, Jimeng
Han, Jiawei
contents The field of relation extraction (RE) is experiencing a notable shift towards generative relation extraction (GRE), leveraging the capabilities of large language models (LLMs). However, we discovered that traditional relation extraction (RE) metrics like precision and recall fall short in evaluating GRE methods. This shortfall arises because these metrics rely on exact matching with human-annotated reference relations, while GRE methods often produce diverse and semantically accurate relations that differ from the references. To fill this gap, we introduce GenRES for a multi-dimensional assessment in terms of the topic similarity, uniqueness, granularity, factualness, and completeness of the GRE results. With GenRES, we empirically identified that (1) precision/recall fails to justify the performance of GRE methods; (2) human-annotated referential relations can be incomplete; (3) prompting LLMs with a fixed set of relations or entities can cause hallucinations. Next, we conducted a human evaluation of GRE methods that shows GenRES is consistent with human preferences for RE quality. Last, we made a comprehensive evaluation of fourteen leading LLMs using GenRES across document, bag, and sentence level RE datasets, respectively, to set the benchmark for future research in GRE
format Preprint
id arxiv_https___arxiv_org_abs_2402_10744
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GenRES: Rethinking Evaluation for Generative Relation Extraction in the Era of Large Language Models
Jiang, Pengcheng
Lin, Jiacheng
Wang, Zifeng
Sun, Jimeng
Han, Jiawei
Computation and Language
Artificial Intelligence
The field of relation extraction (RE) is experiencing a notable shift towards generative relation extraction (GRE), leveraging the capabilities of large language models (LLMs). However, we discovered that traditional relation extraction (RE) metrics like precision and recall fall short in evaluating GRE methods. This shortfall arises because these metrics rely on exact matching with human-annotated reference relations, while GRE methods often produce diverse and semantically accurate relations that differ from the references. To fill this gap, we introduce GenRES for a multi-dimensional assessment in terms of the topic similarity, uniqueness, granularity, factualness, and completeness of the GRE results. With GenRES, we empirically identified that (1) precision/recall fails to justify the performance of GRE methods; (2) human-annotated referential relations can be incomplete; (3) prompting LLMs with a fixed set of relations or entities can cause hallucinations. Next, we conducted a human evaluation of GRE methods that shows GenRES is consistent with human preferences for RE quality. Last, we made a comprehensive evaluation of fourteen leading LLMs using GenRES across document, bag, and sentence level RE datasets, respectively, to set the benchmark for future research in GRE
title GenRES: Rethinking Evaluation for Generative Relation Extraction in the Era of Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2402.10744