用大模型自动映射数据模式，解决可扩展性难题
Towards Scalable Schema Mapping using Large Language Models
- 通过采样聚合降低输入变化对输出的影响
- 支持更复杂的映射表达（如GLaV），突破上下文长度限制
- 用类型预过滤减少调用次数，降低计算开销
随着海量异构数据源的集成需求增长，传统依赖人工编写的数据模式映射面临可扩展性挑战。这些映射复杂、源特定且随源演化难以维护。尽管大语言模型（LLMs）能利用结构与自然语言线索辅助自动匹配，但仍存在三大核心问题：(1) 输出不一致，受输入表述和结构敏感，我们提出采样与聚合方法缓解；(2) 需要更丰富的映射表达（如GLaV），但受限于LLM的有限上下文窗口；(3) 重复调用LLM带来高计算成本，我们通过数据类型预过滤等策略加以缓解。
原文摘要 · Abstract (English)
The growing need to integrate information from a large number of diverse sources poses significant scalability challenges for data integration systems. These systems often rely on manually written schema mappings, which are complex, source-specific, and costly to maintain as sources evolve. While recent advances suggest that large language models (LLMs) can assist in automating schema matching by leveraging both structural and natural language cues, key challenges remain. In this paper, we identify three core issues with using LLMs for schema mapping: (1) inconsistent outputs due to sensitivity to input phrasing and structure, which we propose methods to address through sampling and aggregation techniques; (2) the need for more expressive mappings (e.g., GLaV), which strain the limited context windows of LLMs; and (3) the computational cost of repeated LLM calls, which we propose to mitigate through strategies like data type prefiltering.
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。