Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Can Foundation Models Wrangle Your Data?

About

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.

Avanika Narayan, Ines Chami, Laurel Orr, Simran Arora, Christopher R\'e• 2022

Related benchmarks

TaskDatasetResultRank
ClassificationAdult--
32
Entity MatchingWalmart-Amazon
F1 Score87
14
Error detectionHospital
F1 Score97.8
11
Error detectionFlights
Precision53.7
6
Error detectionBillionaire
Precision43.2
6
Error detectionRayyan
Precision50
6
Error detectionBeers
Precision0.192
6
Error detectionMovies
Precision0.108
6
Error detectionTax
Precision2.7
6
Data ImputationRestaurant
Accuracy88.4
5
Showing 10 of 20 rows

Other info

Code

Follow for update