Guardado en:
Detalles Bibliográficos
Autores principales: Xie, Tingyu, Zhang, Jian, Zhang, Yan, Liang, Yuanyuan, Li, Qi, Wang, Hongwei
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2406.17305
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915041510424576
author Xie, Tingyu
Zhang, Jian
Zhang, Yan
Liang, Yuanyuan
Li, Qi
Wang, Hongwei
author_facet Xie, Tingyu
Zhang, Jian
Zhang, Yan
Liang, Yuanyuan
Li, Qi
Wang, Hongwei
contents The strong capability of large language models (LLMs) has been applied to information extraction (IE) through either retrieval augmented prompting or instruction tuning (IT). However, the best way to incorporate information with LLMs for IE remains an open question. In this paper, we explore Retrieval Augmented Instruction Tuning (RA-IT) for IE, focusing on the task of open named entity recognition (NER). Specifically, for each training sample, we retrieve semantically similar examples from the training dataset as the context and prepend them to the input of the original instruction. To evaluate our RA-IT approach more thoroughly, we construct a Chinese IT dataset for open NER and evaluate RA-IT in both English and Chinese scenarios. Experimental results verify the effectiveness of RA-IT across various data sizes and in both English and Chinese scenarios. We also conduct thorough studies to explore the impacts of various retrieval strategies in the proposed RA-IT framework. Code and data are available at: https://github.com/Emma1066/Retrieval-Augmented-IT-OpenNER
format Preprint
id arxiv_https___arxiv_org_abs_2406_17305
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Retrieval Augmented Instruction Tuning for Open NER with Large Language Models
Xie, Tingyu
Zhang, Jian
Zhang, Yan
Liang, Yuanyuan
Li, Qi
Wang, Hongwei
Computation and Language
The strong capability of large language models (LLMs) has been applied to information extraction (IE) through either retrieval augmented prompting or instruction tuning (IT). However, the best way to incorporate information with LLMs for IE remains an open question. In this paper, we explore Retrieval Augmented Instruction Tuning (RA-IT) for IE, focusing on the task of open named entity recognition (NER). Specifically, for each training sample, we retrieve semantically similar examples from the training dataset as the context and prepend them to the input of the original instruction. To evaluate our RA-IT approach more thoroughly, we construct a Chinese IT dataset for open NER and evaluate RA-IT in both English and Chinese scenarios. Experimental results verify the effectiveness of RA-IT across various data sizes and in both English and Chinese scenarios. We also conduct thorough studies to explore the impacts of various retrieval strategies in the proposed RA-IT framework. Code and data are available at: https://github.com/Emma1066/Retrieval-Augmented-IT-OpenNER
title Retrieval Augmented Instruction Tuning for Open NER with Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2406.17305