KcMF: A Knowledge-compliant Framework for Schema and Entity Matching with Fine-tuning-free LLMs
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929716576911360 |
|---|---|
| author | Xu, Yongqin Li, Huan Chen, Ke Shou, Lidan |
| author_facet | Xu, Yongqin Li, Huan Chen, Ke Shou, Lidan |
| contents | 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%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_12480 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | KcMF: A Knowledge-compliant Framework for Schema and Entity Matching with Fine-tuning-free LLMs Xu, Yongqin Li, Huan Chen, Ke Shou, Lidan Computation and Language Artificial Intelligence Databases Machine Learning 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%. |
| title | KcMF: A Knowledge-compliant Framework for Schema and Entity Matching with Fine-tuning-free LLMs |
| topic | Computation and Language Artificial Intelligence Databases Machine Learning |
| url | https://arxiv.org/abs/2410.12480 |