activity
20142025
most cited"We Have No Idea How Models will Behave in Production until Production": How Engineers Operationalize Machine Learning

23 citations · 64 across the 18 of their papers we have counts for

collaborators
Showing cs.DBShow all

12 papers · 1 filter

cs.DB2025

Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees

Sepanta Zeighami, Shreya Shankar, Aditya Parameswaran

Large Language Models (LLMs) are being increasingly used as a building block in data systems to process large text datasets. To do so, LLM model providers offer multiple LLMs with…

cs.DB20253 cited

The Cambridge Report on Database Research

Anastasia Ailamaki, Samuel Madden, Daniel Abadi +43

On October 19 and 20, 2023, the authors of this report convened in Cambridge, MA, to discuss the state of the database research field, its recent accomplishments and ongoing challe…

cs.DB2024

SPADE: Synthesizing Data Quality Assertions for Large Language Model Pipelines

Shreya Shankar, Haotian Li, Parth Asawa +7

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…

cs.DB202310 cited

Revisiting Prompt Engineering via Declarative Crowdsourcing

Aditya G. Parameswaran, Shreya Shankar, Parth Asawa +2

Large language models (LLMs) are incredibly powerful at comprehending and generating data in the form of text, but are brittle and error-prone. There has been an advent of toolkits…

cs.DB20232 cited

Moving Fast With Broken Data

Shreya Shankar, Labib Fawaz, Karl Gyllstrom +1

Machine learning (ML) models in production pipelines are frequently retrained on the latest partitions of large, continually-growing datasets. Due to engineering bugs, partitions i…

cs.DB20231 cited

Efficient and Compact Spreadsheet Formula Graphs

Dixin Tang, Fanchao Chen, Christopher De Leon +4

Spreadsheets are one of the most popular data analysis tools, wherein users can express computation as formulae alongside data. The ensuing dependencies are tracked as formula grap…