OLAF: Towards Robust LLM-Based Annotation Framework in Empirical Software Engineering

The article introduces OLAF, a framework leveraging Large Language Models (LLMs) for annotation tasks in empirical software engineering. The focus is on robustness, suggesting a need to address challenges like noise and variability in LLM outputs. The research likely explores methods to improve the reliability and consistency of annotations generated by LLMs in this specific domain. The use of 'towards' indicates ongoing work and development.