Structure-Aware Chunking for Tabular Data in Retrieval-Augmented Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913079923572736 |
|---|---|
| author | Guttal, Pooja Magotra, Varun Mahavishnu, Vasudeva Chanto, Natasha Sivaprasad, Sidharth Gaur, Manas |
| author_facet | Guttal, Pooja Magotra, Varun Mahavishnu, Vasudeva Chanto, Natasha Sivaprasad, Sidharth Gaur, Manas |
| contents | Tabular documents such as CSV and Excel files are widely used in enterprise data pipelines, yet existing chunking strategies for retrieval-augmented generation (RAG) are primarily designed for unstructured text and do not account for tabular structure. We propose a structure-aware tabular chunking (STC) framework that operates on row-level units by constructing a hierarchical Row Tree representation, where each row is encoded as a key-value block. STC performs token-constrained splitting aligned with structural boundaries and applies overlap-free greedy merging to produce dense, non-overlapping chunks. This design preserves semantic relationships between fields within a row while improving token utilization and reducing fragmentation. Across evaluations on the MAUD dataset, STC reduces chunk count by up to 40% and 56% compared to standard recursive and key-value based baselines, respectively, while improving token utilization and processing efficiency. In retrieval benchmarks, STC improves MRR from 0.3576 to 0.5945 in a hybrid setting and increases Recall@1 from 0.366 to 0.754 in BM25-only retrieval. These results demonstrate that preserving structure during chunking improves retrieval performance, highlighting the importance of structure-aware chunking for RAG over tabular data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_00318 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Structure-Aware Chunking for Tabular Data in Retrieval-Augmented Generation Guttal, Pooja Magotra, Varun Mahavishnu, Vasudeva Chanto, Natasha Sivaprasad, Sidharth Gaur, Manas Computation and Language Information Retrieval Tabular documents such as CSV and Excel files are widely used in enterprise data pipelines, yet existing chunking strategies for retrieval-augmented generation (RAG) are primarily designed for unstructured text and do not account for tabular structure. We propose a structure-aware tabular chunking (STC) framework that operates on row-level units by constructing a hierarchical Row Tree representation, where each row is encoded as a key-value block. STC performs token-constrained splitting aligned with structural boundaries and applies overlap-free greedy merging to produce dense, non-overlapping chunks. This design preserves semantic relationships between fields within a row while improving token utilization and reducing fragmentation. Across evaluations on the MAUD dataset, STC reduces chunk count by up to 40% and 56% compared to standard recursive and key-value based baselines, respectively, while improving token utilization and processing efficiency. In retrieval benchmarks, STC improves MRR from 0.3576 to 0.5945 in a hybrid setting and increases Recall@1 from 0.366 to 0.754 in BM25-only retrieval. These results demonstrate that preserving structure during chunking improves retrieval performance, highlighting the importance of structure-aware chunking for RAG over tabular data. |
| title | Structure-Aware Chunking for Tabular Data in Retrieval-Augmented Generation |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2605.00318 |