面向大语言模型开放命名实体识别的检索增强指令微调
Retrieval Augmented Instruction Tuning for Open NER with Large Language Models
AI总结：
针对大语言模型信息抽取中如何融合检索信息的问题，本文提出RA-IT框架，通过检索语义相似训练样本增强开放NER的指令微调，并构建中文数据集验证其跨语言和多数据规模的有效性。
摘要：
大语言模型（LLMs）的强大能力已通过检索增强提示或指令微调（IT）应用于信息抽取（IE）。然而，将信息与LLM结合用于IE的最佳方式仍是一个悬而未决的问题。本文探索用于IE的检索增强指令微调（RA-IT），重点关注开放命名实体识别（NER）任务。具体而言，对于每个训练样本，我们从训练数据集中检索语义相似的示例作为上下文，并将其前置到原始指令的输入中。为了更全面地评估RA-IT方法，我们构建了一个用于开放NER的中文IT数据集，并在英文和中文场景中评估RA-IT。实验结果验证了RA-IT在多种数据规模以及英文和中文场景下的有效性。我们还进行了充分研究，以探索所提出的RA-IT框架中各种检索策略的影响。代码和数据可在https://github.com/Emma1066/Retrieval-Augmented-IT-OpenNER获取。
英文摘要：
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
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
