arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.02611cs.LGstat.ML
收藏

LOLA:用于内容实验的大语言模型辅助在线学习算法

LOLA: LLM-Assisted Online Learning Algorithm for Content Experiments

University of Washington(华盛顿大学);University of Toronto(多伦多大学)

Zikun Ye, Hema Yoganarasimhan, Yufeng Zheng

AI总结:

针对纯大语言模型(LLM)无法高精度预测最佳内容的问题,提出LOLA框架,结合最佳纯LLM方法与上置信界算法自适应优化内容交付,在Upworthy数据集上优于现有方法,尤其适用于流量有限场景。

摘要:

现代媒体公司需要自动化且高效的方法来识别对用户最具吸引力的内容。我们利用来自新闻出版商Upworthy的大规模数据集(包含17681个标题A/B测试),首先研究了三种纯大语言模型(LLM)方法识别最吸引人标题的能力:基于提示的方法、基于嵌入的方法和微调的开源LLM。基于提示的方法表现不佳,而基于OpenAI嵌入的模型和微调的Llama-3-8B的准确率仅略高于随机预测。总之,没有任何纯LLM方法能高精度预测表现最佳的标题。随后,我们提出LLM辅助在线学习算法(LOLA),这是一个将LLM与自适应实验相结合以优化内容交付的新型框架。LOLA将最佳纯LLM方法与上置信界算法结合,自适应分配流量并最大化点击量。我们在Upworthy数据上的数值实验表明,LOLA优于标准A/B测试方法(Upworthy当前的现状)、纯bandit算法和纯LLM方法,尤其在实验流量有限的场景中。我们的方法具有可扩展性,适用于企业寻求优化用户参与度的各种内容实验场景,包括数字广告和社交媒体推荐。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑