用指令微调+LoRA让LLaMA-3在金融实体识别上表现超群
Instruction Finetuning LLaMA-3-8B Model Using LoRA for Financial Named Entity Recognition
- 将金融文本转为指令三元组，结合LoRA实现高效微调
- 在1693句数据上达0.894微F1，优于Qwen3、Baichuan2等模型
- 适合金融知识图谱构建者，尤其关注低成本高精度方案
金融命名实体识别（NER）是将非结构化报告和新闻转化为结构化知识图谱的重要方法。然而，免费易用的大语言模型常无法区分组织与个人，或忽略实际金额。本文以Meta的Llama 3 8B为基础，结合指令微调与低秩适配（LoRA）进行金融NER。每条标注语句被转换为指令-输入-输出三元组，使模型在微调时仅更新小规模低秩矩阵，而非全部权重。基于1,693条句子的语料库，该方法取得0.894的微F1分数，优于Qwen3-8B、Baichuan2-7B、T5和BERT-Base。文中还展示了数据集统计、训练超参数设置，并对实体密度、学习曲线与评估指标进行了可视化分析。结果表明，指令微调结合参数高效微调可在领域敏感的NER任务中实现顶尖性能。
原文摘要 · Abstract (English)
Particularly, financial named-entity recognition (NER) is one of the many important approaches to translate unformatted reports and news into structured knowledge graphs. However, free, easy-to-use large language models (LLMs) often fail to differentiate organisations as people, or disregard an actual monetary amount entirely. This paper takes Meta's Llama 3 8B and applies it to financial NER by combining instruction fine-tuning and Low-Rank Adaptation (LoRA). Each annotated sentence is converted into an instruction-input-output triple, enabling the model to learn task descriptions while fine-tuning with small low-rank matrices instead of updating all weights. Using a corpus of 1,693 sentences, our method obtains a micro-F1 score of 0.894 compared with Qwen3-8B, Baichuan2-7B, T5, and BERT-Base. We present dataset statistics, describe training hyperparameters, and perform visualizations of entity density, learning curves, and evaluation metrics. Our results show that instruction tuning combined with parameter-efficient fine-tuning enables state-of-the-art performance on domain-sensitive NER.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。