@inproceedings{wang-etal-2025-icl,
    title = "{ICL}-Bandit: Relevance Labeling in Advertisement Recommendation Systems via {LLM}",
    author = "Wang, Lu  and
      Duan, Chiming  and
      Zhao, Pu  and
      Yang, Fangkai  and
      Shi, Yong  and
      Luo, Xuefeng  and
      Xu, Bingjing  and
      Deng, Weiwei  and
      Lin, Qingwei  and
      Zhang, Dongmei",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.1273/",
    doi = "10.18653/v1/2025.findings-emnlp.1273",
    pages = "23439--23449",
    ISBN = "979-8-89176-335-7",
    abstract = "Measuring the relevance between user queries and advertisements is a critical task for advertisement (ad) recommendation systems, such as Microsoft Bing Ads and Google Ads. Traditionally, this requires expert data labeling, which is both costly and time-consuming. Recent advances have explored using Large Language Models (LLMs) for labeling, but these models often lack domain-specific knowledge. In-context learning (ICL), which involves providing a few demonstrations, is a common practice to enhance LLM performance on domain-specific tasks. However, retrieving high-quality demonstrations in a vast exploration space remains challenging. In this paper, we introduce ICL-Bandit, a practical and effective approach that leverages ICL to enhance the query-ad relevance labeling capabilities of LLMs. We develop a novel bandit learning method to identify and provide superior demonstrations for ICL, thereby improving labeling performance. Experimental results demonstrate that ICL-Bandit achieves state-of-the-art performance compared to existing methods. Additionally, ICL-Bandit has been deployed in Company X, that serves billions of users worldwide, confirming its robustness and effectiveness."
}