The use of LLMs for natural language processing has become a popular trend in
the past two years, driven by their formidable capacity for context
comprehension and learning, which has inspired a wave of research from
academics and industry professionals. However, for certain NLP tasks, such as
NER, the performance of LLMs still falls short when compared to supervised
learning methods. In our research, we developed a NER processing framework
called LTNER that incorporates a revolutionary Contextualized Entity Marking
Gen Method. By leveraging the cost-effective GPT-3.5 coupled with context
learning that does not require additional training, we significantly improved
the accuracy of LLMs in handling NER tasks. The F1 score on the CoNLL03 dataset
increased from the initial 85.9% to 91.9%, approaching the performance of
supervised fine-tuning. This outcome has led to a deeper understanding of the
potential of LLMs.

LLMs 在自然语言处理中的应用已成为近两年的热门趋势，然而，对于某些 NLP 任务，如 NER，在与监督学习方法相比较时，LLMs 的性能仍然不足以胜任。我们的研究开发了一种名为 LTNER 的 NER 处理框架，该框架融入了一种革命性的上下文化实体标记生成方法，通过利用成本效益高的 GPT-3.5 以及无需额外训练的上下文学习，显著提高了 LLMs 在处理 NER 任务时的准确性。在 CoNLL03 数据集上的 F1 得分从初始的 85.9% 增加到 91.9%，接近了监督微调的性能，这一结果增进了对 LLMs 潜力的深入认识。