Retrieval Augmented Instruction Tuning for Open NER with Large Language Models
This work addresses the challenge of optimizing information extraction with LLMs for researchers and practitioners in NLP, though it appears incremental as it builds on existing retrieval and instruction tuning methods.
The paper tackles the problem of incorporating information with large language models for information extraction by proposing Retrieval Augmented Instruction Tuning (RA-IT) for open named entity recognition, achieving effectiveness across various data sizes and in both English and Chinese scenarios as verified by experimental results.
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