Creating a Taxonomy for Retrieval Augmented Generation Applications
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_ | 1866916618626400256 |
|---|---|
| author | Nikishina, Irina Sevgili, Özge Li, Mahei Manhai Biemann, Chris Semmann, Martin |
| author_facet | Nikishina, Irina Sevgili, Özge Li, Mahei Manhai Biemann, Chris Semmann, Martin |
| contents | In this research, we develop a taxonomy to conceptualize a comprehensive overview of the constituting characteristics that define retrieval augmented generation (RAG) applications, facilitating the adoption of this technology for different application domains. To the best of our knowledge, no holistic RAG application taxonomies have been developed so far. We employ the method foreign to ACL and thus contribute to the set of methods in the taxonomy creation. It comprises four iterative phases designed to refine and enhance our understanding and presentation of RAG's core dimensions. We have developed a total of five meta-dimensions and sixteen dimensions to comprehensively capture the concept of RAG applications. Thus, the taxonomy can be used to better understand RAG applications and to derive design knowledge for future solutions in specific application domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_02854 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Creating a Taxonomy for Retrieval Augmented Generation Applications Nikishina, Irina Sevgili, Özge Li, Mahei Manhai Biemann, Chris Semmann, Martin Information Retrieval In this research, we develop a taxonomy to conceptualize a comprehensive overview of the constituting characteristics that define retrieval augmented generation (RAG) applications, facilitating the adoption of this technology for different application domains. To the best of our knowledge, no holistic RAG application taxonomies have been developed so far. We employ the method foreign to ACL and thus contribute to the set of methods in the taxonomy creation. It comprises four iterative phases designed to refine and enhance our understanding and presentation of RAG's core dimensions. We have developed a total of five meta-dimensions and sixteen dimensions to comprehensively capture the concept of RAG applications. Thus, the taxonomy can be used to better understand RAG applications and to derive design knowledge for future solutions in specific application domains. |
| title | Creating a Taxonomy for Retrieval Augmented Generation Applications |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2408.02854 |