In the rapidly evolving digital content landscape, media firms and news publishers require automated and efficient methods to enhance user engagement. This study introduces the LLM-Assisted Online Learning Algorithm (LOLA), a novel framework that integrates Large Language Models (LLMs) with adaptive experimentation to optimize content delivery. Leveraging a large-scale dataset from Upworthy, which includes 17,681 headline A/B tests, the study investigates three pure-LLM approaches and finds that prompt-based methods perform poorly, while embedding-based classification models and fine-tuned open-source LLMs achieve higher accuracy.
LOLA combines the best pure-LLM approach with the Upper Confidence Bound (UCB) algorithm to allocate traffic and maximize clicks adaptively. Numerical experiments on data from the website Upworthy show that LOLA outperforms the standard A/B test method, pure bandit algorithms and pure-LLM approaches, particularly in scenarios with limited experimental traffic. This scalable approach is applicable to content experiments across various settings where firms seek to optimize user engagement, including digital advertising and social media recommendations.
Member Only Access
