Foundation Models for Tabular Data within Systemic Contexts Need Grounding

• URL: http://arxiv.org/abs/2505.19825v1
• Date: Mon, 26 May 2025 11:02:51 GMT
• Title: Foundation Models for Tabular Data within Systemic Contexts Need Grounding
• Authors: Tassilo Klein, Johannes Hoffart,
• Abstract summary: We introduce the concept of Semantically Linked Tables (SLT), recognizing that tables are inherently connected to both declarative and procedural operational knowledge.<n>We propose Foundation Models for Semantically Linked Tables (FMSLT), which integrate these components to ground data within its true operational context.
• Score: 9.820997523824676
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current research on tabular foundation models often overlooks the complexities of large-scale, real-world data by treating tables as isolated entities and assuming information completeness, thereby neglecting the vital operational context. To address this, we introduce the concept of Semantically Linked Tables (SLT), recognizing that tables are inherently connected to both declarative and procedural operational knowledge. We propose Foundation Models for Semantically Linked Tables (FMSLT), which integrate these components to ground tabular data within its true operational context. This comprehensive representation unlocks the full potential of machine learning for complex, interconnected tabular data across diverse domains. Realizing FMSLTs requires access to operational knowledge that is often unavailable in public datasets, highlighting the need for close collaboration between domain experts and researchers. Our work exposes the limitations of current tabular foundation models and proposes a new direction centered on FMSLTs, aiming to advance robust, context-aware models for structured data.

Related papers

• A Pre-training Framework for Relational Data with Information-theoretic Principles [57.93973948947743]
  We introduce Task Vector Estimation (TVE), a novel pre-training framework that constructs supervisory signals via set-based aggregation over relational graphs.<n>TVE consistently outperforms traditional pre-training baselines.<n>Our findings advocate for pre-training objectives that encode task heterogeneity and temporal structure as design principles for predictive modeling on relational databases.
  arXiv  Detail & Related papers  (2025-07-14T00:17:21Z)
• Generating Synthetic Relational Tabular Data via Structural Causal Models [0.0]
  We develop a novel framework that generates realistic synthetic relational data including causal relationships across tables.<n>Our experiments confirm that this framework is able to construct relational datasets with complex inter-table dependencies mimicking real-world scenarios.
  arXiv  Detail & Related papers  (2025-07-04T12:27:23Z)
• Multimodal Tabular Reasoning with Privileged Structured Information [67.40011423365712]
  We introduce TabUlar Reasoning with Bridged infOrmation (sc Turbo)<n>sc Turbo benefits from a structure-aware reasoning trace generator based on DeepSeek-R1.<n>sc Turbo achieves state-of-the-art performance ($+7.2%$ vs. previous SOTA) across multiple datasets.
  arXiv  Detail & Related papers  (2025-06-04T15:46:30Z)
• Representation Learning for Tabular Data: A Comprehensive Survey [23.606506938919605]
  Tabular data, structured as rows and columns, is among the most prevalent data types in machine learning classification and regression applications.<n>Deep Neural Networks (DNNs) have recently demonstrated promising results through their capability of representation learning.<n>We organize existing methods into three main categories according to their generalization capabilities.
  arXiv  Detail & Related papers  (2025-04-17T17:58:23Z)
• LLM-TabFlow: Synthetic Tabular Data Generation with Inter-column Logical Relationship Preservation [49.898152180805454]
  This study is the first to explicitly address inter-column relationship preservation in synthetic tabular data generation.<n>LLM-TabFlow is a novel approach that captures complex inter-column relationships and compress data, while using Score-based Diffusion to model the distribution of the compressed data in latent space.<n>Our results show that LLM-TabFlow outperforms all baselines, fully preserving inter-column relationships while achieving the best balance between data fidelity, utility, and privacy.
  arXiv  Detail & Related papers  (2025-03-04T00:47:52Z)
• SALT: Sales Autocompletion Linked Business Tables Dataset [7.036380633387952]
  We introduce a curated dataset sourced from an Enterprise Resource Planning (ERP) system, featuring extensive linked tables.<n>Our goal is to potentially enhance the effectiveness and applicability of models for real-world business contexts.
  arXiv  Detail & Related papers  (2025-01-06T22:20:02Z)
• Knowledge-Aware Reasoning over Multimodal Semi-structured Tables [85.24395216111462]
  This study investigates whether current AI models can perform knowledge-aware reasoning on multimodal structured data. We introduce MMTabQA, a new dataset designed for this purpose. Our experiments highlight substantial challenges for current AI models in effectively integrating and interpreting multiple text and image inputs.
  arXiv  Detail & Related papers  (2024-08-25T15:17:43Z)
• Synthesizing Realistic Data for Table Recognition [4.500373384879752]
  We propose a novel method for synthesizing annotation data specifically designed for table recognition. By leveraging the structure and content of tables from Chinese financial announcements, we have developed the first extensive table annotation dataset. We have established the inaugural benchmark for real-world complex tables in the Chinese financial announcement domain, using it to assess the performance of models trained on our synthetic data.
  arXiv  Detail & Related papers  (2024-04-17T06:36:17Z)
• 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)
• Serving Deep Learning Model in Relational Databases [70.53282490832189]
  Serving deep learning (DL) models on relational data has become a critical requirement across diverse commercial and scientific domains. We highlight three pivotal paradigms: The state-of-the-art DL-centric architecture offloads DL computations to dedicated DL frameworks. The potential UDF-centric architecture encapsulates one or more tensor computations into User Defined Functions (UDFs) within the relational database management system (RDBMS)
  arXiv  Detail & Related papers  (2023-10-07T06:01:35Z)
• CateCom: a practical data-centric approach to categorization of computational models [77.34726150561087]
  We present an effort aimed at organizing the landscape of physics-based and data-driven computational models. We apply object-oriented design concepts and outline the foundations of an open-source collaborative framework.
  arXiv  Detail & Related papers  (2021-09-28T02:59:40Z)

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.