4 papers · 1 filter
FALCON: A Model and Dataset Agnostic Framework for Synthetic Data Generation for NL2SQL Pairs
Darian Lee, Shannon Rumsey, Jack St. Clair +3
Relational databases are among the most widely deployed forms of structured knowledge, and natural language access to them requires grounding language onto schema entities and rela…
REALMS: An AI-Assistant Conversational System for Real-Time Exact Audience Sizing over High-Dimensional Nested Profiles
Haixu Ma, Aditya Bansal, Shubham Lohiya +1
Audience sizing is a critical component of digital marketing. It enables precise resource allocation, campaign planning, and performance optimization. Traditional approaches using…
Skill-based Agentic Evaluation for Real-time Data Science Tasks
Aniruddha Tamhane, Raghavendra Addanki, Ayushi Aggarwal +4
We present a framework for evaluating data-science agents on live, continuously updated data using executable ground truth and format-agnostic factoid scoring. Consider this exampl…
Human-LLM Collaborative Feature Engineering for Tabular Data
Zhuoyan Li, Aditya Bansal, Jinzhao Li +8
Large language models (LLMs) are increasingly used to automate feature engineering in tabular learning. Given task-specific information, LLMs can propose diverse feature transforma…