arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.09282cs.CL
收藏

通过知识蒸馏和优化训练策略利用大型语言模型提升NLP任务性能

Leveraging Large Language Models for Enhanced NLP Task Performance through Knowledge Distillation and Optimized Training Strategies

School of Politics and Public Administration, South China Normal University(华南师范大学政治与公共管理学院);University of Chinese Academy of Sciences(中国科学院大学);Shenyang institute of computing technology, Chinese academy of sciences(中国科学院沈阳计算技术研究所)

Yining Huang, Keke Tang, Meilian Chen

AI总结:

本研究提出三阶段训练策略,利用GPT-4标注数据蒸馏给BERT模型,发现蒸馏与原始数据的简单混合策略显著提升NER性能,降低标注成本。

摘要:

诸如GPT-4等新兴大型语言模型彻底改变了自然语言处理(NLP),在命名实体识别(NER)等传统任务中展现出潜力。我们的研究探索了一种三阶段训练策略,利用GPT-4的能力来增强BERT模型在NER上的性能。首先,GPT-4在未进行微调的情况下对CONLL2003的一个子集和额外的BBC数据集进行标注。随后,我们使用原始数据和LLM标注数据的混合来训练BERT,分析LLM标注相对于传统方法的有效性。第二阶段涉及不同训练方案的对比实验,评估蒸馏数据与原始数据之间的协同作用。我们观察到,顺序策略(特别是先使用蒸馏数据再使用原始数据进行训练的简单混合)显著提升了性能。在第三阶段,我们研究了各种数据混合技术,包括sigmoid和power decay函数,以进一步优化训练过程。结果表明,蒸馏数据与原始数据的战略性混合显著提升了BERT的NER能力。该方法提供了一种可扩展的方法,降低了人工标注成本并提高了效率,使其在资源有限和封闭网络环境中尤为适用。研究得出结论,尽管“简单混合”策略取得了最佳结果,但理解其潜在机制仍需进一步研究。未来的工作还将集中于完善提示设计和增强标注选择过程,旨在将该方法扩展到多种NLP任务。

英文摘要:

Emerging Large Language Models (LLMs) like GPT-4 have revolutionized Natural Language Processing (NLP), showing potential in traditional tasks such as Named Entity Recognition (NER). Our study explores a three-phase training strategy that harnesses GPT-4's capabilities to enhance the BERT model's performance on NER. Initially, GPT-4 annotates a subset of the CONLL2003 and additional BBC dataset without fine-tuning. We then train BERT using a mix of original and LLM-annotated data, analyzing the efficacy of LLM annotations against traditional methods. The second phase involves comparative experiments with different training regimens, assessing the synergy between distilled and original data. We observe that sequential strategies, particularly a simple mix of training first with distilled data followed by original data, significantly boost performance. In the third phase, we investigate various data blending techniques, including sigmoid and power decay functions, to optimize the training process further. Our results indicate that a strategic mix of distilled and original data markedly elevates the NER capabilities of BERT. Our approach presents a scalable methodology that reduces manual annotation costs and increases efficiency, making it especially pertinent in resource-limited and closed-network environments. The study concludes that while the 'Simple Mix' strategy yields the best results, understanding its underlying mechanisms requires further research. Future work will also focus on refining prompt designs and enhancing annotation selection processes, aiming to extend our methodology to diverse NLP tasks.

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。

↑