Alonso Silva
Alonso Silva is currently a Researcher on Verifiable AI at Nokia Bell Labs in the Machine Learning and Systems Research Lab. He has previously worked at Safran in the Department of Mathematics and Temporal Data, in the Department of Electrical Engineering and Computer Sciences at the University of California, Berkeley, working with Professor Jean Walrand, at INRIA Paris Rocquencourt working with Dr. Philippe Jacquet and as a Research Consultant/Intern at Bell Labs Headquarters in Murray Hill, New Jersey, working with Dr. Iraj Saniee. He did his Ph.D. at INRIA Sophia-Antipolis under the direction of Dr. Eitan Altman. He obtained his Ph.D. degree in Physics from the École Supérieure d'Électricité in June 2010.
Session
Processing large volumes of unstructured or semi-structured data into analysis-ready dataframes remains a core challenge in modern data pipelines. Structured outputs (leveraging the function/tool-calling capabilities of LLMs) and structured generation (which guarantees 100% valid JSON by constraining token sampling to a predefined schema) offer powerful, complementary solutions to this challenge.
In this talk, we introduce both methods, discuss their respective advantages and limitations in the context of batch data processing, and demonstrate why combining both approaches yields superior results compared to either method alone. To illustrate these concepts, we present real-world applications including:
Batch data extraction from unstructured text into structured dataframe columns
Large-scale text classification for categorical feature engineering
Entity and relationship extraction to enrich dataframes for downstream analytics
A live demonstration will showcase an end-to-end pipeline processing real datasets, highlighting throughput, schema compliance, and integration with standard dataframe libraries (e.g., pandas, Polars).