Towards Requirements Engineering for RAG Systems
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910938520616960 |
|---|---|
| author | Sporsem, Tor Ulfsnes, Rasmus |
| author_facet | Sporsem, Tor Ulfsnes, Rasmus |
| contents | This short paper explores how a maritime company develops and integrates large-language models (LLM). Specifically by looking at the requirements engineering for Retrieval Augmented Generation (RAG) systems in expert settings. Through a case study at a maritime service provider, we demonstrate how data scientists face a fundamental tension between user expectations of AI perfection and the correctness of the generated outputs. Our findings reveal that data scientists must identify context-specific "retrieval requirements" through iterative experimentation together with users because they are the ones who can determine correctness. We present an empirical process model describing how data scientists practically elicited these "retrieval requirements" and managed system limitations. This work advances software engineering knowledge by providing insights into the specialized requirements engineering processes for implementing RAG systems in complex domain-specific applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_07553 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Requirements Engineering for RAG Systems Sporsem, Tor Ulfsnes, Rasmus Software Engineering Artificial Intelligence This short paper explores how a maritime company develops and integrates large-language models (LLM). Specifically by looking at the requirements engineering for Retrieval Augmented Generation (RAG) systems in expert settings. Through a case study at a maritime service provider, we demonstrate how data scientists face a fundamental tension between user expectations of AI perfection and the correctness of the generated outputs. Our findings reveal that data scientists must identify context-specific "retrieval requirements" through iterative experimentation together with users because they are the ones who can determine correctness. We present an empirical process model describing how data scientists practically elicited these "retrieval requirements" and managed system limitations. This work advances software engineering knowledge by providing insights into the specialized requirements engineering processes for implementing RAG systems in complex domain-specific applications. |
| title | Towards Requirements Engineering for RAG Systems |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2505.07553 |