Work

Sentence to Model: Cost-Effective Data Collection LLM Agent

Year: 2025

Type: conference-paper

Abstract: We introduce Sentence-to-Model, an automated system that converts natural language queries into tabular datasets and predictive models. The system utilizes LLM agents for planning and active learning to prioritize data collection under budget constraints, such as API costs and rate limits. By integrating resources, it generates datasets and trains machine learning models with minimal human intervention. Sentence-to-Model streamlines data collection and enables the refinement of user needs and easy exploration of the data landscape. Our approach highlights the potential of combining LLMs with algorithmic techniques for efficient data science workflows.

Source: Proceedings - ACM-SIGMOD International Conference on Management of Data

DOI: 10.1145/3722212.3725134

Authors: Yael Einy, Guy Dar, Slava Novgorodov, Tova Milo

Institution: Tel Aviv University

Language: English

Topic: Machine Learning and Algorithms

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W4411374424

FWCI: 1.059

Cites: 4

Cited by: 1

Related to: 10