# Evaluating Chunking Strategies For Retrieval-Augmented Generation in Oil and Gas Enterprise Documents

arXiv: https://arxiv.org/abs/2603.24556 · HTML: https://mlsanity.com/paper/2603.24556/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 18 of its 24 references that are in the map.
- First posted on arXiv 25 Mar 2026.

## Placed in

- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)

## Builds on (most cited first, 18 of 18)

- [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)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Internet-augmented language models through few-shot prompting for open-domain question answering](https://mlsanity.com/paper/2203.05115/) (2022)
- [RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation](https://mlsanity.com/paper/2408.08067/) (2024)
- [Is Semantic Chunking Worth the Computational Cost?](https://mlsanity.com/paper/2410.13070/) (2024)
- [The Chronicles of RAG: The Retriever, the Chunk and the Generator](https://mlsanity.com/paper/2401.07883/) (2024)
- [Analysing the Robustness of Dual Encoders for Dense Retrieval Against Misspellings](https://mlsanity.com/paper/2205.02303/) (2022)
- [Adaptive Contrastive Decoding in Retrieval-Augmented Generation for Handling Noisy Contexts](https://mlsanity.com/paper/2408.01084/) (2024)
- [MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System](https://mlsanity.com/paper/2503.09600/) (2025)
- [Question-Based Retrieval using Atomic Units for Enterprise RAG](https://mlsanity.com/paper/2405.12363/) (2024)
- [BERM: Training the Balanced and Extractable Representation for Matching to Improve Generalization Ability of Dense Retrieval](https://mlsanity.com/paper/2305.11052/) (2023)
- [S2 Chunking: A Hybrid Framework for Document Segmentation Through Integrated Spatial and Semantic Analysis](https://mlsanity.com/paper/2501.05485/) (2025)
- [Optimizing and Evaluating Enterprise Retrieval-Augmented Generation (RAG): A Content Design Perspective](https://mlsanity.com/paper/2410.12812/) (2024)
- [Vision-Guided Chunking Is All You Need: Enhancing RAG with Multimodal Document Understanding](https://mlsanity.com/paper/2506.16035/) (2025)
- [Talking like Piping and Instrumentation Diagrams (P&IDs)](https://mlsanity.com/paper/2502.18928/) (2025)
- [Dynamic Chunking and Selection for Reading Comprehension of Ultra-Long Context in Large Language Models](https://mlsanity.com/paper/2506.00773/) (2025)
- [Advancing Retrieval-Augmented Generation for Structured Enterprise and Internal Data](https://mlsanity.com/paper/2507.12425/) (2025)

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

- [Inject or Navigate? Token-Efficient Retrieval for LLM Analysis of Transactional Legal Documents](https://mlsanity.com/paper/2607.05764/) (2026)

## Abstract (arXiv)

Retrieval-Augmented Generation (RAG) has emerged as a framework to address the constraints of Large Language Models (LLMs). Yet, its effectiveness fundamentally hinges on document chunking - an often-overlooked determinant of its quality. This paper presents an empirical study quantifying performance differences across four chunking strategies: fixed-size sliding window, recursive, breakpoint-based semantic, and structure-aware. We evaluated these methods using a proprietary corpus of oil and gas enterprise documents, including text-heavy manuals, table-heavy specifications, and piping and instrumentation diagrams (P and IDs). Our findings show that structure-aware chunking yields higher overall retrieval effectiveness, particularly in top-K metrics, and incurs significantly lower computational costs than semantic or baseline strategies. Crucially, all four methods demonstrated limited effectiveness on P and IDs, underscoring a core limitation of purely text-based RAG within visually and spatially encoded documents. We conclude that while explicit structure preservation is essential for specialised domains, future work must integrate multimodal models to overcome current limitations.