LOLA: LLM-Assisted Online Learning Algorithm for Content Experiments

AmazUtah_NLP at SemEval-2024 Task 9: A MultiChoice Question Answering System for Commonsense Defying Reasoning


View a PDF of the paper titled LOLA: LLM-Assisted Online Learning Algorithm for Content Experiments, by Zikun Ye and 2 other authors

View PDF
HTML (experimental)

Abstract:Modern media firms require automated and efficient methods to identify content that is most engaging and appealing to users. Leveraging a large-scale dataset from Upworthy (a news publisher), which includes 17,681 headline A/B tests, we first investigate the ability of three pure-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 Large Language Models (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.

Submission history

From: Zikun Ye [view email]
[v1]
Mon, 3 Jun 2024 07:56:58 UTC (2,999 KB)
[v2]
Fri, 26 Jul 2024 00:26:10 UTC (738 KB)
[v3]
Tue, 26 Nov 2024 18:51:57 UTC (897 KB)



Source link
lol

By stp2y

Leave a Reply

Your email address will not be published. Required fields are marked *

No widgets found. Go to Widget page and add the widget in Offcanvas Sidebar Widget Area.