PIPER: Content-Based Table Search via profiling and LLM-Generated Pseudoqueries

• URL: http://arxiv.org/abs/2605.18199v1
• Date: Mon, 18 May 2026 10:39:42 GMT
• Title: PIPER: Content-Based Table Search via profiling and LLM-Generated Pseudoqueries
• Abstract summary: Existing dataset search systems rely mainly on metadata, which is often incomplete or low quality.<n>We propose PIPER, a content-driven retrieval method that uses table profiles and LLM-generated queries embedded for dense retrieval.
• Score: 0.6299766708197881
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid growth of tabular datasets in data lakes, data spaces, and open data portals makes effective dataset search essential for reuse and analysis. Existing search systems rely mainly on metadata, which is often incomplete or low quality, especially for tables whose meaning depends on both schema and cell values. Recent advances in Large Language Models (LLMs) enable richer, content-based representations of tables. However, prior LLM-based retrieval methods have focused on Table Question Answering, where the goal is to select a single table to answer a question, rather than retrieve and rank relevant datasets. We propose PIPER, a content-driven retrieval method for tabular datasets that uses table profiles and LLM-generated queries embedded for dense retrieval. Designed for dataset search in poor-metadata settings, PIPER outperforms both classical metadata-based baselines and strong TableQA retrieval methods, demonstrating the value of LLM-based content modeling for tabular dataset search.

Related papers

• Polaris: Learning to Generate Table Descriptions from Retrieval Feedback [1.361581623990238]
  We present Polaris, a system that trains an LLM to generate table descriptions directly from retrieval feedback.<n>Our key insight is that existing table retrieval benchmarks already contain the supervision needed for this task.<n>Extensive experiments show that Polaris outperforms the state-of-the-art AutoDDG solution, often by a significant margin.
  arXiv  Detail & Related papers  (2026-08-17T22:13:01Z)
• FGTR: Fine-Grained Multi-Table Retrieval via Hierarchical LLM Reasoning [9.827204445321147]
  Fine-Grained Multi-Table Retrieval FGTR is a new retrieval paradigm that employs a human-like reasoning strategy.<n> Experimental results show that FGTR outperforms previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-03-13T06:28:45Z)
• Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs [66.63911043019294]
  Data preparation aims to denoise raw datasets, uncover cross-dataset relationships, and extract valuable insights from them.<n>This paper focuses on the use of LLM techniques to prepare data for diverse downstream tasks.<n>We introduce a task-centric taxonomy that organizes the field into three major tasks: data cleaning, standardization, error processing, imputation, data integration, and data enrichment.
  arXiv  Detail & Related papers  (2026-01-22T12:02:45Z)
• A Hybrid Search for Complex Table Question Answering in Securities Report [0.9430947207126281]
  We propose a cell extraction method for Table Question Answering (TQA) without manual identification.<n>Our approach estimates table headers by computing similarities between a given question and individual cells.<n>We then select as the answer the cells at the intersection of the most relevant row and column.
  arXiv  Detail & Related papers  (2025-11-12T10:19:27Z)
• Keywords are not always the key: A metadata field analysis for natural language search on open data portals [3.974422712382188]
  We examine how individual metadata fields affect the success of conversational dataset retrieval.<n>We compare existing content of the metadata field 'description' with LLM-generated content.<n>Our findings suggest that dataset descriptions play a central role in aligning with user intent.
  arXiv  Detail & Related papers  (2025-09-17T22:14:27Z)
• Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End System [8.096082871461311]
  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.
  arXiv  Detail & Related papers  (2025-04-12T13:20:50Z)
• 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)
• RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking [63.253294691180635]
  In real-world scenarios, beyond pure text, a substantial amount of knowledge is stored in tables.<n>We first propose a table-corpora-aware RAG framework, named T-RAG, which consists of the hierarchical memory index, multi-stage retrieval, and graph-aware prompting.
  arXiv  Detail & Related papers  (2025-04-02T04:24:41Z)
• Extract Information from Hybrid Long Documents Leveraging LLMs: A Framework and Dataset [52.286323454512996]
  Large Language Models (LLMs) can comprehend and analyze hybrid text, containing textual and tabular data.<n>We propose an Automated Information Extraction framework (AIE) to enable LLMs to process the hybrid long documents (HLDs) and carry out experiments to analyse four important aspects of information extraction from HLDs.<n>To address the issue of dataset scarcity in HLDs and support future work, we also propose the Financial Reports Numerical Extraction (FINE) dataset.
  arXiv  Detail & Related papers  (2024-12-28T07:54:14Z)
• 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)
• 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)

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.