# Can Large Language Models Improve SE Active Learning via Warm-Starts?

arXiv: https://arxiv.org/abs/2501.00125 · HTML: https://mlsanity.com/paper/2501.00125/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Dec 2024.

## Built on by (most cited first, 2 of 2)

- [Training-Free Active Learning Framework in Materials Science with Large Language Models](https://mlsanity.com/paper/2511.19730/) (2025)
- [When to Use Which? Benchmarking Optimisers for Configurable Systems under Varying Budgets](https://mlsanity.com/paper/2607.16476/) (2026)

## Abstract (arXiv)

When SE data is scarce, "active learners" use models learned from tiny samples of the data to find the next most informative example to label. In this way, effective models can be generated using very little data. For multi-objective software engineering (SE) tasks, active learning can benefit from an effective set of initial guesses (also known as "warm starts"). This paper explores the use of Large Language Models (LLMs) for creating warm-starts. Those results are compared against Gaussian Process Models and Tree of Parzen Estimators. For 49 SE tasks, LLM-generated warm starts significantly improved the performance of low- and medium-dimensional tasks. However, LLM effectiveness diminishes in high-dimensional problems, where Bayesian methods like Gaussian Process Models perform best.