Search papers, labs, and topics across Lattice.
PrismaDV generates task-aware data unit tests by analyzing downstream task code and dataset profiles to identify data access patterns and infer implicit data assumptions. To adapt the tests over time, they introduce SIFTA, a prompt-optimization framework that leverages execution outcomes from data unit tests and downstream tasks. Experiments on 60 tasks across five datasets demonstrate that PrismaDV outperforms task-agnostic and task-aware baselines, and that SIFTA learns prompts that outperform human-written or generically optimized prompts.
Automatically generate data unit tests that actually catch the data errors that matter for your specific downstream tasks.
Data is a central resource for modern enterprises, and data validation is essential for ensuring the reliability of downstream applications. However, existing automated data unit testing frameworks are largely task-agnostic: they validate datasets without considering the semantics and requirements of the code that consumes the data. We present PrismaDV, a compound AI system that analyzes downstream task code together with dataset profiles to identify data access patterns, infer implicit data assumptions, and generate task-aware executable data unit tests. To further adapt the data unit tests over time to specific datasets and downstream tasks, we propose"Selective Informative Feedback for Task Adaptation"(SIFTA), a prompt-optimization framework that leverages the scarce outcomes from the execution of data unit tests and downstream tasks. We evaluate PrismaDV on two new benchmarks spanning 60 tasks across five datasets, where it consistently outperforms both task-agnostic and task-aware baselines in generating unit tests that reflect the end-to-end impact of data errors. Furthermore, we show that with SIFTA, we can automatically learn prompts for PrismaDV's modules that outperform prompts written by hand or generated from a generic prompt optimizer. We publicly release our benchmarks and prototype implementation.