@inproceedings{malik-etal-2024-pearl,
    title = "{PEARL}: Preference Extraction with Exemplar Augmentation and Retrieval with {LLM} Agents",
    author = "Malik, Vijit  and
      Jagatap, Akshay  and
      Puranik, Vinayak S  and
      Majumder, Anirban",
    editor = "Dernoncourt, Franck  and
      Preo{\c{t}}iuc-Pietro, Daniel  and
      Shimorina, Anastasia",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = nov,
    year = "2024",
    address = "Miami, Florida, US",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.emnlp-industry.112/",
    doi = "10.18653/v1/2024.emnlp-industry.112",
    pages = "1536--1547",
    abstract = "Identifying preferences of customers in their shopping journey is a pivotal aspect in providing product recommendations. The task becomes increasingly challenging when there is a multi-turn conversation between the user and a shopping assistant chatbot. In this paper, we tackle a novel and complex problem of identifying customer preferences in the form of key-value filters on an e-commerce website in a multi-turn conversational setting. Existing systems specialize in extracting customer preferences from standalone customer queries which makes them unsuitable to multi-turn setup. We propose PEARL (Preference Extraction with ICL Augmentation and Retrieval with LLM Agents) that leverages collaborative LLM agents, generates in-context learning exemplars and dynamically retrieves relevant exemplars during inference time to extract customer preferences as a combination of key-value filters. Our experiments on proprietary and public datasets show that PEARL not only improves performance on exact match by {\textasciitilde}10{\%} compared to competitive LLM-based baselines but additionally improves inference latency by {\textasciitilde}110{\%}."
}