Can Foundation Models Wrangle Your Data?

2022/05/20 by Avanika Narayan, Ines Chami, Narayan, Avanika +5 · 15 citations
Computer Science · Decision Sciences · Medicine · #Artificial Intelligence (cs.AI) #Artificial Intelligence in Healthcare and Education #Data Quality and Management #Databases (cs.DB) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data

paper · pdf · doi:10.48550/arxiv.2205.09911

openalex publication_date 2022/05/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Foundation Models (FMs) are models trained on large corpora of data that, at very large scale, can generalize to new tasks without any task-specific finetuning. As these models continue to grow in size, innovations continue to push the boundaries of what these models can do on language and image tasks. This paper aims to understand an underexplored area of FMs: classical data tasks like cleaning and integration. As a proof-of-concept, we cast five data cleaning and integration tasks as prompting tasks and evaluate the performance of FMs on these tasks. We find that large FMs generalize and achieve SoTA performance on data cleaning and integration tasks, even though they are not trained for these data tasks. We identify specific research challenges and opportunities that these models present, including challenges with private and domain specific data, and opportunities to make data management systems more accessible to non-experts. We make our code and experiments publicly available at: https://github.com/HazyResearch/fm_data_tasks.

Cited by

• Ensembling LLM-Induced Decision Trees for Explainable and Robust Error Detection
• Featurized-Decomposition Join: Low-Cost Semantic Joins with Guarantees
• BookRAG: A Hierarchical Structure-aware Index-based Approach for Retrieval-Augmented Generation on Complex Documents
• Structured Multi-Step Reasoning for Entity Matching Using Large Language Model
• Schema Matching on Graph: Iterative Graph Exploration for Efficient and Explainable Data Integration
• The Rapid Growth of AI Foundation Model Usage in Science
• Connecting the herd and the habitat: A plea for an AI-driven framework for integrating livestock and biodiversity data
• A Survey of Data Agents: Emerging Paradigm or Overstated Hype?
• Confidence Calibration in Large Language Model-Based Entity Matching
• Improving Table Understanding with LLMs and Entity-Oriented Search
• Planning for Success: Exploring LLM Long-term Planning Capabilities in Table Understanding
• Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees
• Transduction is All You Need for Structured Data Workflows
• Omni Geometry Representation Learning vs Large Language Models for Geospatial Entity Resolution
• BDIViz: An Interactive Visualization System for Biomedical Schema Matching with LLM-Powered Validation

Related

• Synergizing Foundation Models and Federated Learning: A Survey
• CHORUS: Foundation Models for Unified Data Discovery and Exploration
• Foundation models in brief: A historical, socio-technical focus
• Specialized Foundation Models Struggle to Beat Supervised Baselines
• Fine-tuning can cripple your foundation model; preserving features may be the solution