无需微调的LLM框架，解决数据匹配中的幻觉与指令混淆问题
KcMF: A Knowledge-compliant Framework for Schema and Entity Matching with Fine-tuning-free LLMs
- 用伪代码分解任务，引导LLM推理减少混淆
- 通过数据与样例构建领域知识，提升匹配准确率
- 多源结果集成策略抑制错误输出，适合数据集成场景
模式匹配（SM）和实体匹配（EM）是数据集成的关键任务。尽管大语言模型（LLMs）在这些任务中表现优异，但仍存在幻觉和对任务指令理解混乱的问题。本文提出无需领域微调的常识合规匹配框架（KcMF），采用一次性的伪代码任务分解策略，以自然语言引导LLM推理，降低不同任务类型间的混淆。提出两种机制：将数据作为知识（DaK）和将样例作为知识（EaK），在缺乏结构化领域知识时构建知识集。此外，引入结果集成策略，融合多个知识源并抑制格式错误输出。大量实验表明，KcMF显著提升五种LLM骨干模型在SM和EM任务中的性能，平均F1得分比非LLM方法高出17.93%。
原文摘要 · Abstract (English)
Schema matching (SM) and entity matching (EM) tasks are crucial for data integration. While large language models (LLMs) have shown promising results in these tasks, they suffer from hallucinations and confusion about task instructions. This study presents the Knowledge-Compliant Matching Framework (KcMF), an LLM-based approach that addresses these issues without the need for domain-specific fine-tuning. KcMF employs a once-and-for-all pseudo-code-based task decomposition strategy to adopt natural language statements that guide LLM reasoning and reduce confusion across various task types. We also propose two mechanisms, Dataset as Knowledge (DaK) and Example as Knowledge (EaK), to build domain knowledge sets when unstructured domain knowledge is lacking. Moreover, we introduce a result-ensemble strategy to leverage multiple knowledge sources and suppress badly formatted outputs. Extensive evaluations confirm that KcMF clearly enhances five LLM backbones in both SM and EM tasks while outperforming the non-LLM competitors by an average F1-score of 17.93%.
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。