# Data Quality Challenges in Retrieval-Augmented Generation

arXiv: https://arxiv.org/abs/2510.00552 · HTML: https://mlsanity.com/paper/2510.00552/

## 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 15 of its 46 references that are in the map.
- First posted on arXiv 1 Oct 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, 15 of 15)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [Ragas: Automated Evaluation of Retrieval Augmented Generation](https://mlsanity.com/paper/2309.15217/) (2023)
- [Seven Failure Points When Engineering a Retrieval Augmented Generation System](https://mlsanity.com/paper/2401.05856/) (2024)
- [Trustworthiness in Retrieval-Augmented Generation Systems: A Survey](https://mlsanity.com/paper/2409.10102/) (2024)
- [Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely](https://mlsanity.com/paper/2409.14924/) (2024)
- [The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunities](https://mlsanity.com/paper/2408.13296/) (2024)
- [Data-centric AI: Perspectives and Challenges](https://mlsanity.com/paper/2301.04819/) (2023)
- [Data-Centric Artificial Intelligence](https://mlsanity.com/paper/2212.11854/) (2022)
- [A Study on the Implementation of Generative AI Services Using an Enterprise Data-Based LLM Application Architecture](https://mlsanity.com/paper/2309.01105/) (2023)
- [RAG Does Not Work for Enterprises](https://mlsanity.com/paper/2406.04369/) (2024)
- [Speech Retrieval-Augmented Generation without Automatic Speech Recognition](https://mlsanity.com/paper/2412.16500/) (2024)
- [Artificial Intelligence Governance for Businesses](https://mlsanity.com/paper/2011.10672/) (2020)
- [A Survey of LLM Alignment: Instruction Understanding, Intention Reasoning, and Reliable Generation](https://mlsanity.com/paper/2502.09101/) (2025)

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

- [Detecting Clinical Discrepancies in Health Coaching Agents: A Dual-Stream Memory and Reconciliation Architecture](https://mlsanity.com/paper/2604.27045/) (2026)

## Abstract (arXiv)

Organizations increasingly adopt Retrieval-Augmented Generation (RAG) to enhance Large Language Models with enterprise-specific knowledge. However, current data quality (DQ) frameworks have been primarily developed for static datasets, and only inadequately address the dynamic, multi-stage nature of RAG systems. This study aims to develop DQ dimensions for this new type of AI-based systems. We conduct 16 semi-structured interviews with practitioners of leading IT service companies. Through a qualitative content analysis, we inductively derive 15 distinct DQ dimensions across the four processing stages of RAG systems: data extraction, data transformation, prompt & search, and generation. Our findings reveal that (1) new dimensions have to be added to traditional DQ frameworks to also cover RAG contexts; (2) these new dimensions are concentrated in early RAG steps, suggesting the need for front-loaded quality management strategies, and (3) DQ issues transform and propagate through the RAG pipeline, necessitating a dynamic, step-aware approach to quality management.