Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End System

• URL: http://arxiv.org/abs/2504.09207v1
• Date: Sat, 12 Apr 2025 13:20:50 GMT
• Title: Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End System
• Authors: Muhammad Imam Luthfi Balaka, David Alexander, Qiming Wang, Yue Gong, Adila Krisnadhi, Raul Castro Fernandez,
• Abstract summary: Pneuma is a retrieval-augmented generation (RAG) system designed to efficiently and effectively discover tabular data.<n>For table representation, Pneuma preserves schema and row-level information to ensure comprehensive data understanding.<n>For table retrieval, Pneuma augments LLMs with traditional information retrieval techniques, such as full-text and vector search.
• Score: 8.096082871461311
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Finding relevant tables among databases, lakes, and repositories is the first step in extracting value from data. Such a task remains difficult because assessing whether a table is relevant to a problem does not always depend only on its content but also on the context, which is usually tribal knowledge known to the individual or team. While tools like data catalogs and academic data discovery systems target this problem, they rely on keyword search or more complex interfaces, limiting non-technical users' ability to find relevant data. The advent of large language models (LLMs) offers a unique opportunity for users to ask questions directly in natural language, making dataset discovery more intuitive, accessible, and efficient. In this paper, we introduce Pneuma, a retrieval-augmented generation (RAG) system designed to efficiently and effectively discover tabular data. Pneuma leverages large language models (LLMs) for both table representation and table retrieval. For table representation, Pneuma preserves schema and row-level information to ensure comprehensive data understanding. For table retrieval, Pneuma augments LLMs with traditional information retrieval techniques, such as full-text and vector search, harnessing the strengths of both to improve retrieval performance. To evaluate Pneuma, we generate comprehensive benchmarks that simulate table discovery workload on six real-world datasets including enterprise data, scientific databases, warehousing data, and open data. Our results demonstrate that Pneuma outperforms widely used table search systems (such as full-text search and state-of-the-art RAG systems) in accuracy and resource efficiency.

Related papers

• Bridging Queries and Tables through Entities in Table Retrieval [70.13748256886288]
  Entities are well-studied in the context of text retrieval, but there is a noticeable lack of research on their applications in table retrieval.<n>We propose an entity-enhanced training framework and design an interaction paradigm based on entity representations.<n>Our proposed framework is plug-and-play and flexible, making it easy to integrate into existing table retriever training processes.
  arXiv  Detail & Related papers  (2025-04-09T03:16:33Z)
• GTR: Graph-Table-RAG for Cross-Table Question Answering [53.11230952572134]
  We propose the first Graph-Table-RAG framework, namely GTR, which reorganizes table corpora into a heterogeneous graph. GTR exhibits superior cross-table question-answering performance while maintaining high deployment efficiency, demonstrating its real-world practical applicability.
  arXiv  Detail & Related papers  (2025-04-02T04:24:41Z)
• 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)
• RoundTable: Leveraging Dynamic Schema and Contextual Autocomplete for Enhanced Query Precision in Tabular Question Answering [11.214912072391108]
  Real-world datasets often feature a vast array of attributes and complex values. Traditional methods cannot fully relay the datasets size and complexity to the Large Language Models. We propose a novel framework that leverages Full-Text Search (FTS) on the input table.
  arXiv  Detail & Related papers  (2024-08-22T13:13:06Z)
• DiscoveryBench: Towards Data-Driven Discovery with Large Language Models [50.36636396660163]
  We present DiscoveryBench, the first comprehensive benchmark that formalizes the multi-step process of data-driven discovery. Our benchmark contains 264 tasks collected across 6 diverse domains, such as sociology and engineering. Our benchmark, thus, illustrates the challenges in autonomous data-driven discovery and serves as a valuable resource for the community to make progress.
  arXiv  Detail & Related papers  (2024-07-01T18:58:22Z)
• Enhancing Knowledge Retrieval with In-Context Learning and Semantic Search through Generative AI [3.9773527114058855]
  We propose a novel methodology that combines the generative capabilities of Large Language Models with the fast and accurate retrieval capabilities of vector databases. The developed model, Generative Text Retrieval (GTR), is adaptable to both unstructured and structured data with minor refinement. The refined model, Generative Tabular Text Retrieval (GTR-T), demonstrated its efficiency in large database querying.
  arXiv  Detail & Related papers  (2024-06-13T23:08:06Z)
• OpenTab: Advancing Large Language Models as Open-domain Table Reasoners [38.29047314758911]
  OpenTab is an open-domain table reasoning framework powered by Large Language Models (LLMs) OpenTab significantly outperforms baselines in both open- and closed-domain settings, achieving up to 21.5% higher accuracy.
  arXiv  Detail & Related papers  (2024-02-22T08:01:01Z)
• TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning [55.33939289989238]
  We propose TAP4LLM as a versatile pre-processor suite for leveraging large language models (LLMs) in table-based tasks effectively. It covers several distinct components: (1) table sampling to decompose large tables into manageable sub-tables based on query semantics, (2) table augmentation to enhance tables with additional knowledge from external sources or models, and (3) table packing & serialization to convert tables into various formats suitable for LLMs' understanding.
  arXiv  Detail & Related papers  (2023-12-14T15:37:04Z)
• DataFinder: Scientific Dataset Recommendation from Natural Language Descriptions [100.52917027038369]
  We operationalize the task of recommending datasets given a short natural language description. To facilitate this task, we build the DataFinder dataset which consists of a larger automatically-constructed training set and a smaller expert-annotated evaluation set. This system, trained on the DataFinder dataset, finds more relevant search results than existing third-party dataset search engines.
  arXiv  Detail & Related papers  (2023-05-26T05:22:36Z)
• Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQA [85.17249272519626]
  An optimized OpenQA Table-Text Retriever (OTTeR) is proposed. We conduct retrieval-centric mixed-modality synthetic pre-training. OTTeR substantially improves the performance of table-and-text retrieval on the OTT-QA dataset.
  arXiv  Detail & Related papers  (2022-10-11T07:04:39Z)

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.