将LLM-SC应用于活态神圣遗产：帕舒帕蒂纳特神庙评论的领域特定提取、语义网络与人工评估
内容导读
大语言模型（LLM）流水线可将访客评论转化为结构化数据，但通用方案可能遗漏活态神圣遗产地的仪式、神圣空间、文化限制及情感复杂的体验。我们针对尼泊尔帕舒帕蒂纳特神庙调整了LLM-社会计算（LLM-SC）框架，设定了包含12类实体的分类体系（4类原始LLM-SC类型及8类神圣遗产类型）、4类关系和9个方面—情感维度，并在GPT-4o提取提示中……
对照原文
Adapting LLM-SC to Living Sacred Heritage: Domain-Specific Extraction, Semantic Networks and Human Evaluation on Pashupatinath Temple Reviews
Large language model (LLM) pipelines can turn visitor reviews into structured data, but generic schemes may miss rituals, sacred spaces, cultural restrictions and emotionally mixed experiences at living sacred heritage sites. We adapted the LLM-Social Computing (LLM-SC) framework to Pashupatinath Temple, Nepal, by specifying a 12-type entity taxonomy (four original LLM-SC types plus eight sacred-heritage types), four relation types and nine aspect-sentiment dimensions in a GPT-4o extraction prom…
SOURCES · 01
相关来源
- 01arXiv · AI 文旅预印本原文
arxiv.org