# Mind the Gap: Bridging Behavioral Silos with LLMs in Multi-Vertical Recommendations

arXiv: https://arxiv.org/abs/2606.06779 · HTML: https://mlsanity.com/paper/2606.06779/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 15 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Builds on (most cited first, 7 of 7)

- [Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate](https://mlsanity.com/paper/1804.07931/) (2018)
- [Retrieval-Augmented Generation with Hierarchical Knowledge](https://mlsanity.com/paper/2503.10150/) (2025)
- [ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation](https://mlsanity.com/paper/2502.09891/) (2025)
- [Exploring the Impact of Large Language Models on Recommender Systems: An Extensive Review](https://mlsanity.com/paper/2402.18590/) (2024)
- [Large Language Model Simulator for Cold-Start Recommendation](https://mlsanity.com/paper/2402.09176/) (2024)
- [A Survey on LLM-based News Recommender Systems](https://mlsanity.com/paper/2502.09797/) (2025)
- [Event-based Product Carousel Recommendation with Query-Click Graph](https://mlsanity.com/paper/2402.03277/) (2024)

## Abstract (arXiv)

In multi-vertical e-commerce platforms like DoorDash, relatively newer product verticals such as grocery and retail present a significant opportunity for personalization innovation. A key challenge lies in solving the "cold start" problem for users. This paper introduces a novel framework for enhancing recommendation quality by transferring knowledge from data-rich verticals (e.g., restaurants at DoorDash) to data-sparse ones. We leverage Large Language Models (LLMs) to perform generative inference, synthesizing sparse, high-dimensional features that encapsulate latent user affinities. Specifically, we employ a hierarchical Retrieval-Augmented Generation (RAG) pipeline to derive multi-level taxonomic features from user restaurant order histories and search queries. These generated features, encoding both long-term cross-vertical preferences and short-term intent, are integrated into a production Multi-Task Learning (MTL) ranking model. We demonstrate through extensive offline and online evaluation that this approach significantly improves personalization and engagement in emerging business verticals, effectively bridging the behavioral data gap.