📚 Selected Work
Check out my google scholar for a full list of my publications here. Here are some of my key publications in areas where I have been deeply involved.
Data Validation for LLM Pipelines
-
SPADE: Synthesizing Data Quality Assertions for Large Language Model Pipelines
To appear at VLDB 2024Shreya Shankar, Haotian Li, Parth Asawa, Madelon Hulsebos, Yiming Lin, J.D. Zamfirescu-Pereira, Harrison Chase, Will Fu-Hinthorn, Aditya G. Parameswaran, Eugene Wu -
What We've Learned From a Year of Building with LLMs
O'Reilly RadarEugene Yan, Bryan Bischof, Charles Frye, Hamel Husain, Jason Liu, Shreya Shankar -
Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences
HEAL Workshop at CHI 2024 (Full paper under submission)Shreya Shankar, J.D. Zamfirescu-Pereira, Björn Hartmann, Aditya G. Parameswaran, Ian Arawjo
Scalable Data Processing with LLMs
-
Building Reactive Large Language Model Pipelines with Motion
SIGMOD 2024 (Demo)Shreya Shankar, Aditya G. Parameswaran -
Revisiting Prompt Engineering via Declarative Crowdsourcing
CIDR 2023Aditya G. Parameswaran, Shreya Shankar, Parth Asawa, Naman Jain, Yujie Wang
Traditional MLOps
-
Operationalizing Machine Learning: An Interview Study
To appear at CSCW 2024Shreya Shankar*, Rolando Garcia*, Joseph M. Hellerstein, Aditya G. Parameswaran -
Automatic and Precise Data Validation for Machine Learning
CIKM 2023Shreya Shankar, Labib Fawaz, Karl Gyllstrom, Aditya G. Parameswaran -
Towards Observability for Production Machine Learning Pipelines
VLDB 2023Shreya Shankar, Aditya G. Parameswaran -
Bolt-on, Compact, and Rapid Program Slicing for Notebooks
VLDB 2023Shreya Shankar*, Stephen Macke*, Sarah Chasins, Andrew Head, Aditya G. Parameswaran -
Rethinking Streaming Machine Learning Evaluation
ICLR 2022: Workshop on ML Evaluation StandardsShreya Shankar, Bernease Herman, Aditya G. Parameswaran
Undergraduate Research
-
Adversarial examples that fool both computer vision and time-limited humans
NIPS 2018Gamalelden F. Elsayed, Shreya Shankar, Brian Cheung, Nicolas Papernot, Alexey Kurakin, Ian Goodfellow, Jascha Sohl-Dickstein -
No classification without representation: Assessing geodiversity issues in open data sets for the developing world
NIPS 2017: Workshop on Machine Learning for the Developing WorldShreya Shankar, Yoni Halpern, Eric Breck, James Atwood, Jimbo Wilson, D. Sculley