Webinars
LOLA: LLM-Assisted Online Learning Algorithm for Content Experiments
Modern media firms require automated and efficient methods to identify content that is most engaging and appealing to users. Leveraging a large-scale data set from Upworthy (a news publisher), which includes 17,681 headline A/B tests, we first investigate the ability of three pure–large language model (LLM) approaches to identify the catchiest headline: prompt-based methods, embedding-based methods, and fine-tuned open-source LLMs. Prompt-based approaches perform poorly, while both OpenAI embedding–based models and the fine-tuned Llama-3-8B achieve marginally higher accuracy than random predictions. In sum, none of the pure LLM–based methods can predict the best-performing headline with high accuracy. We then introduce the LLM-assisted online learning algorithm (LOLA), a novel framework that integrates LLMs with adaptive experimentation to optimize content delivery. LOLA combines the best pure-LLM approach with the upper confidence bound algorithm to allocate traffic and maximize clicks adaptively. Our numerical experiments on Upworthy data show that LOLA outperforms the standard A/B test method (the current status quo at Upworthy), pure bandit algorithms, and pure-LLM approaches, particularly in scenarios with limited experimental traffic. Our approach is scalable and applicable to content experiments across various settings where firms seek to optimize user engagement, including digital advertising and social media recommendations.
speaker
Hema Yoganarasimhan is a faculty member at the Foster School of Business at the University of Washington. She is recognized as one of the leading experts in quantitative marketing. Hema’s research brings together large-scale marketing data, economic theory, econometrics, generative AI, and machine learning tools to help firms optimize and automate their marketing decisions. She currently serves as a senior editor at Marketing Science. Her recent work covers a wide variety of topics, including mobile advertising, content optimization, adaptive pricing and promotions, combining bandits and LLMs to improve experimentation, measurement of media polarization using image data, and personalized policy design for search rankings, promotions, and social media. Together, her recent body of work presents creative yet technically viable solutions to the challenges that businesses face in today’s world.