PEARL: Preference Extraction with Exemplar Augmentation and Retrieval with LLM Agents

Vijit Malik, Akshay Jagatap, Vinayak S Puranik, Anirban Majumder


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 ~10% compared to competitive LLM-based baselines but additionally improves inference latency by ~110%.
Anthology ID:
2024.emnlp-industry.112
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track
Month:
November
Year:
2024
Address:
Miami, Florida, US
Editors:
Franck Dernoncourt, Daniel Preoţiuc-Pietro, Anastasia Shimorina
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1536–1547
Language:
URL:
https://aclanthology.org/2024.emnlp-industry.112
DOI:
Bibkey:
Cite (ACL):
Vijit Malik, Akshay Jagatap, Vinayak S Puranik, and Anirban Majumder. 2024. PEARL: Preference Extraction with Exemplar Augmentation and Retrieval with LLM Agents. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 1536–1547, Miami, Florida, US. Association for Computational Linguistics.
Cite (Informal):
PEARL: Preference Extraction with Exemplar Augmentation and Retrieval with LLM Agents (Malik et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-industry.112.pdf