TabRAG: Tabular Document Retrieval via Structured Language Representations

• URL: http://arxiv.org/abs/2511.06582v1
• Date: Mon, 10 Nov 2025 00:05:58 GMT
• Title: TabRAG: Tabular Document Retrieval via Structured Language Representations
• Abstract summary: Ingesting data for Retrieval-Augmented Generation (RAG) involves either fine-tuning the embedding model directly on the target corpus or parsing documents for embedding model encoding.<n>We present TabRAG, a parsing-based RAG pipeline designed to tackle table-heavy documents via structured language representations.
• Score: 12.83985785007887
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Ingesting data for Retrieval-Augmented Generation (RAG) involves either fine-tuning the embedding model directly on the target corpus or parsing documents for embedding model encoding. The former, while accurate, incurs high computational hardware requirements, while the latter suffers from suboptimal performance when extracting tabular data. In this work, we address the latter by presenting TabRAG, a parsing-based RAG pipeline designed to tackle table-heavy documents via structured language representations. TabRAG outperforms existing popular parsing-based methods for generation and retrieval. Code is available at https://github.com/jacobyhsi/TabRAG.

Related papers

• Towards Pretraining Text Encoders for TabPFN [78.5840707720685]
  Tabular foundation models, such as TabPFN, achieve strong performance on datasets with numerical and categorical data.<n>We introduce the TabPFN Text Adapter (text-to-TFM token projection)<n>This design removes the PCA bottleneck, preserves TabPFN's numerical strengths, and is more efficient to train than end-to-end text-tabular pipelines.
  arXiv  Detail & Related papers  (2026-06-03T13:38:47Z)
• MoDora: Tree-Based Semi-Structured Document Analysis System [62.01015188258797]
  Semi-structured documents integrate diverse interleaved data elements arranged in various and often irregular layouts.<n>MoDora is an LLM-powered system for semi-structured document analysis.<n> Experiments show MoDora outperforms baselines by 5.97%-61.07% in accuracy.
  arXiv  Detail & Related papers  (2026-02-26T14:48:49Z)
• TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning [7.706148486477738]
  Retrieval-Augmented Generation (RAG) has demonstrated considerable effectiveness in open-domain question answering.<n>Existing RAG approaches exhibit critical limitations when applied to heterogeneous documents.
  arXiv  Detail & Related papers  (2025-06-12T06:16:49Z)
• Mixture-of-RAG: Integrating Text and Tables with Large Language Models [5.038576104344948]
  Heterogeneous Document RAG requires joint retrieval and reasoning across textual and hierarchical data.<n>We propose MixRAG, a novel three-stage framework that preserves hierarchical structure and heterogeneous relationships.<n>Experiments show that MixRAG boosts top-1 retrieval by 46% over strong text-only, table-only, and naive-mixture baselines.
  arXiv  Detail & Related papers  (2025-04-13T13:02:33Z)
• PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Paths [42.01377074786958]
  Retrieval-augmented generation (RAG) improves the response quality of large language models (LLMs) by retrieving knowledge from external databases.<n>We propose PathRAG, which retrieves key relational paths from the indexing graph, and converts these paths into textual form for prompting LLMs.<n>PathRAG consistently outperforms state-of-the-art baselines across six datasets and five evaluation dimensions.
  arXiv  Detail & Related papers  (2025-02-18T11:18:55Z)
• VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents [66.42579289213941]
  Retrieval-augmented generation (RAG) is an effective technique that enables large language models to utilize external knowledge sources for generation.<n>We introduce VisRAG, which tackles this issue by establishing a vision-language model (VLM)-based RAG pipeline.<n>In this pipeline, instead of first parsing the document to obtain text, the document is directly embedded using a VLM as an image and then retrieved to enhance the generation of a VLM.
  arXiv  Detail & Related papers  (2024-10-14T15:04:18Z)
• Less is More: Making Smaller Language Models Competent Subgraph Retrievers for Multi-hop KGQA [51.3033125256716]
  We model the subgraph retrieval task as a conditional generation task handled by small language models. Our base generative subgraph retrieval model, consisting of only 220M parameters, competitive retrieval performance compared to state-of-the-art models. Our largest 3B model, when plugged with an LLM reader, sets new SOTA end-to-end performance on both the WebQSP and CWQ benchmarks.
  arXiv  Detail & Related papers  (2024-10-08T15:22:36Z)
• TableRAG: Million-Token Table Understanding with Language Models [53.039560091592215]
  TableRAG is a Retrieval-Augmented Generation (RAG) framework specifically designed for LM-based table understanding.<n>TableRAG leverages query expansion combined with schema and cell retrieval to pinpoint crucial information before providing it to the LMs.<n>Our results demonstrate that TableRAG achieves the highest retrieval quality, leading to the new state-of-the-art performance on large-scale table understanding.
  arXiv  Detail & Related papers  (2024-10-07T04:15:02Z)
• Beyond Extraction: Contextualising Tabular Data for Efficient Summarisation by Language Models [0.0]
  The conventional use of the Retrieval-Augmented Generation architecture has proven effective for retrieving information from diverse documents. This research introduces an innovative approach to enhance the accuracy of complex table queries in RAG-based systems.
  arXiv  Detail & Related papers  (2024-01-04T16:16:14Z)
• TabGenie: A Toolkit for Table-to-Text Generation [2.580765958706854]
  TabGenie is a toolkit which enables researchers to explore, preprocess, and analyze a variety of data-to-text generation datasets. It is equipped with command line processing tools and Python bindings for unified dataset loading and processing.
  arXiv  Detail & Related papers  (2023-02-27T22:05:46Z)
• Autoregressive Search Engines: Generating Substrings as Document Identifiers [53.0729058170278]
  Autoregressive language models are emerging as the de-facto standard for generating answers. Previous work has explored ways to partition the search space into hierarchical structures. In this work we propose an alternative that doesn't force any structure in the search space: using all ngrams in a passage as its possible identifiers.
  arXiv  Detail & Related papers  (2022-04-22T10:45:01Z)
• ToTTo: A Controlled Table-To-Text Generation Dataset [61.83159452483026]
  ToTTo is an open-domain English table-to-text dataset with over 120,000 training examples. We introduce a dataset construction process where annotators directly revise existing candidate sentences from Wikipedia. While usually fluent, existing methods often hallucinate phrases that are not supported by the table.
  arXiv  Detail & Related papers  (2020-04-29T17:53:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.