Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces a Large Language Model (LLM)-based re-ranking system designed to enhance conversational recommendations in real estate search by effectively interpreting user intent across multi-turn dialogues. The authors constructed a large-scale evaluation dataset comprising 960,000 query-item pairs, validated through both an LLM-as-a-Judge framework and human annotations. The results from offline evaluations and an online A/B test indicate a significant improvement in ranking quality, with a +5.3% increase in click-through rates and a +4.8% rise in scheduled visits, underscoring the importance of context in user interactions.
Integrating conversational context into real estate search can boost user engagement metrics by over 5%.
QuintoAndar Group operates the leading housing marketplace in Latin America for both rentals and sales. The platform replaces traditionally paper-heavy workflows with a fully digital experience, making housing transactions faster and more accessible to tenants, buyers, and landlords in the region. Finding the ideal home in such a vast catalog is inherently difficult. At the same time, the widespread adoption of conversational assistants is reshaping user expectations: people increasingly want to express their needs through open, multi-turn dialog rather than rigid filter menus and faceted search. This shift is particularly pronounced in housing, where intent is multi-dimensional, context-dependent, and rarely reducible to a small set of structured constraints. To meet these expectations, we propose a Large Language Model (LLM) based re-ranker that augments a conversational recommendation system by reordering retrieved candidates according to the nuanced, context-rich intent expressed across the user's conversation. We additionally construct a large-scale offline evaluation dataset for conversational real-estate search, containing 960,000 query-item pairs constructed from both synthetic and production queries and annotated using an LLM-as-a-Judge framework with human validation. We validate our approach both offline, on this proprietary dataset, and online, through a production A/B test. Both evaluations show consistent improvements in ranking quality, including a statistically significant increase in production of +5.3% in click-through rate and +4.8% in scheduled visits, demonstrating the value of integrating conversational context into housing recommendations.