REVIEW 7 cited by
Can Foundation Models Wrangle Your Data?
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original 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.
Forward citations
Cited by 7 Pith papers
-
Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees
BARGAIN uses betting-based anytime-valid tests and adaptive, target-aware sampling to set model-cascade thresholds, delivering non-asymptotic quality guarantees and up to 86% greater cost savings than SUPG.
-
Ensembling LLM-Induced Decision Trees for Explainable and Robust Error Detection
LLM-induced hybrid decision trees (rules + trained graph checks) ensembled via EM detect erroneous table cells with an average 16.1-point F1 gain over the best baseline.
-
The Case for Instance-Optimized LLMs in OLAP Databases
IOLM-DB compresses a general-purpose LLM on a per-query basis to speed up LLM-invoking OLAP queries, reporting throughput gains up to 3.31x and smaller models in a three-workload prototype.
-
A Generative Approach for Semantic Auditing of Electronic Health Records
Medical Data Pecking uses LLM-generated, literature-grounded tests to audit EHRs for semantic gaps, flagging discrepancies between observed data and epidemiological priors.
-
TransClean: Finding False Positives in Multi-Source Entity Matching under Real-World Conditions via Transitive Consistency
TransClean uses a model's predictions on transitive, implied record pairs to locate and remove false positive matches in multi-source entity resolution.
-
LLaPipe: LLM-Guided Reinforcement Learning for Automated Data Preparation Pipeline Construction
A framework that uses LLM suggestions, retrieved past experience, and adaptive triggering to speed up RL search for data preprocessing pipelines, showing improved accuracy on 18 tabular datasets.
-
An Empirical study on LLM-based Log Retrieval for Software Engineering Metadata Management
A natural-language log retrieval pipeline using LLM-generated video and signal descriptions shows that prompt and model choice matter, but its proposed reliability metrics are not validated against any ground truth.
Discussion (0). Sign in to comment.