SPADE: Synthesizing Data Quality Assertions for Large Language Model Pipelines
January 05, 2024 ยท Declared Dead ยท ๐ Proceedings of the VLDB Endowment
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Shreya Shankar, Haotian Li, Parth Asawa, Madelon Hulsebos, Yiming Lin, J. D. Zamfirescu-Pereira, Harrison Chase, Will Fu-Hinthorn, Aditya G. Parameswaran, Eugene Wu
arXiv ID
2401.03038
Category
cs.DB: Databases
Cross-listed
cs.SE
Citations
24
Venue
Proceedings of the VLDB Endowment
Last Checked
3 months ago
Abstract
Large language models (LLMs) are being increasingly deployed as part of pipelines that repeatedly process or generate data of some sort. However, a common barrier to deployment are the frequent and often unpredictable errors that plague LLMs. Acknowledging the inevitability of these errors, we propose {\em data quality assertions} to identify when LLMs may be making mistakes. We present SPADE, a method for automatically synthesizing data quality assertions that identify bad LLM outputs. We make the observation that developers often identify data quality issues during prototyping prior to deployment, and attempt to address them by adding instructions to the LLM prompt over time. SPADE therefore analyzes histories of prompt versions over time to create candidate assertion functions and then selects a minimal set that fulfills both coverage and accuracy requirements. In testing across nine different real-world LLM pipelines, SPADE efficiently reduces the number of assertions by 14\% and decreases false failures by 21\% when compared to simpler baselines. SPADE has been deployed as an offering within LangSmith, LangChain's LLM pipeline hub, and has been used to generate data quality assertions for over 2000 pipelines across a spectrum of industries.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Databases
R.I.P.
๐ป
Ghosted
R.I.P.
๐ป
Ghosted
The Case for Learned Index Structures
R.I.P.
๐ป
Ghosted
Untangling Blockchain: A Data Processing View of Blockchain Systems
R.I.P.
๐ป
Ghosted
Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades
R.I.P.
๐ป
Ghosted
BLOCKBENCH: A Framework for Analyzing Private Blockchains
R.I.P.
๐ป
Ghosted
Data Synthesis based on Generative Adversarial Networks
Died the same way โ ๐ป Ghosted
R.I.P.
๐ป
Ghosted
Language Models are Few-Shot Learners
R.I.P.
๐ป
Ghosted
PyTorch: An Imperative Style, High-Performance Deep Learning Library
R.I.P.
๐ป
Ghosted
XGBoost: A Scalable Tree Boosting System
R.I.P.
๐ป
Ghosted