为构建特定领域知识图谱对大型语言模型进行监督微调：以湖南历史名人案例研究
Supervised Fine Tuning of Large Language Models for Domain Specific Knowledge Graph Construction:A Case Study on Hunan's Historical Celebrities
AI总结：
本研究通过监督微调提升大型语言模型在湖南历史名人领域知识提取能力，验证了参数高效方法在低资源环境下的有效性。
摘要：
大型语言模型和知识图谱为通过支持文化遗产的提取、分析和解释来推进历史文化研究提供了强大潜力。以受湖湘文化影响的湖南现代历史名人作为案例研究，预训练大型模型可以帮助研究人员从文本来源中高效提取关键信息，包括传记属性、生平事件和社会关系，并构建结构化知识图谱。然而，针对湖南历史名人的系统数据资源仍然有限，通用模型在低资源设置中往往在领域知识提取和结构化输出生成方面表现不佳。为了解决这些问题，本研究提出了一种监督微调方法，以增强领域特定信息提取。首先，我们设计了一个细粒度、以模式指导的指令模板，专门针对湖南历史名人领域，并构建了一个指令微调数据集，以缓解缺乏领域特定训练语料的不足。其次，我们对四个公开可用的大型语言模型——Qwen2.5-7B、Qwen3-8B、DeepSeek-R1-Distill-Qwen-7B和Llama-3.1-8B-Instruct应用参数高效指令微调，并开发了评估其提取性能的评估标准。实验结果表明，所有模型在微调后均表现出显著的性能提升。其中，Qwen3-8B取得了最强的成果，达到100个样本和50次训练迭代时的89.3866分。本研究为垂直大型语言模型在区域历史和文化领域的微调提供了新的见解，并突显了其在文化遗产知识提取和知识图谱构建中的潜在应用价值。
英文摘要：
Large language models and knowledge graphs offer strong potential for advancing research on historical culture by supporting the extraction, analysis, and interpretation of cultural heritage. Using Hunan's modern historical celebrities shaped by Huxiang culture as a case study, pre-trained large models can help researchers efficiently extract key information, including biographical attributes, life events, and social relationships, from textual sources and construct structured knowledge graphs. However, systematic data resources for Hunan's historical celebrities remain limited, and general-purpose models often underperform in domain knowledge extraction and structured output generation in such low-resource settings. To address these issues, this study proposes a supervised fine-tuning approach for enhancing domain-specific information extraction. First, we design a fine-grained, schema-guided instruction template tailored to the Hunan historical celebrities domain and build an instruction-tuning dataset to mitigate the lack of domain-specific training corpora. Second, we apply parameter-efficient instruction fine-tuning to four publicly available large language models - Qwen2.5-7B, Qwen3-8B, DeepSeek-R1-Distill-Qwen-7B, and Llama-3.1-8B-Instruct - and develop evaluation criteria for assessing their extraction performance. Experimental results show that all models exhibit substantial performance gains after fine-tuning. Among them, Qwen3-8B achieves the strongest results, reaching a score of 89.3866 with 100 samples and 50 training iterations. This study provides new insights into fine-tuning vertical large language models for regional historical and cultural domains and highlights their potential for cost-effective applications in cultural heritage knowledge extraction and knowledge graph construction.
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。
