# Towards Requirements Engineering for RAG Systems

arXiv: https://arxiv.org/abs/2505.07553 · HTML: https://mlsanity.com/paper/2505.07553/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation.
- Builds on 12 of its 32 references that are in the map.
- First posted on arXiv 12 May 2025.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 12 of 12)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Benchmarking Large Language Models in Retrieval-Augmented Generation](https://mlsanity.com/paper/2309.01431/) (2023)
- [Seven Failure Points When Engineering a Retrieval Augmented Generation System](https://mlsanity.com/paper/2401.05856/) (2024)
- [Requirements Engineering for Machine Learning: Perspectives from Data Scientists](https://mlsanity.com/paper/1908.04674/) (2019)
- [A Software Engineering Perspective on Engineering Machine Learning Systems: State of the Art and Challenges](https://mlsanity.com/paper/2012.07919/) (2020)
- [RAG based Question-Answering for Contextual Response Prediction System](https://mlsanity.com/paper/2409.03708/) (2024)
- [Requirements Practices and Gaps When Engineering Human-Centered Artificial Intelligence Systems](https://mlsanity.com/paper/2301.10404/) (2023)
- [Transforming Software Development with Generative AI: Empirical Insights on Collaboration and Workflow](https://mlsanity.com/paper/2405.01543/) (2024)
- [Naming the Pain in Machine Learning-Enabled Systems Engineering](https://mlsanity.com/paper/2406.04359/) (2024)
- [Teaching Theorizing in Software Engineering Research](https://mlsanity.com/paper/2406.17174/) (2024)

## Built on by (most cited first, 1 of 1)

- [Towards Energy-aware Requirements Dependency Classification: Knowledge-Graph vs. Vector-Retrieval Augmented Inference with SLMs](https://mlsanity.com/paper/2603.23954/) (2026)

## Abstract (arXiv)

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.