RALLM-POI: Retrieval-Augmented LLM for Zero-shot Next POI Recommendation with Geographical Reranking
This work addresses the challenge of making accurate and geographically relevant next POI recommendations for users without additional training, though it is incremental as it builds on existing LLM and retrieval techniques.
The paper tackled the problem of zero-shot next point-of-interest recommendation, where traditional models require intensive training and LLMs often produce generic or geographically irrelevant results, by proposing RALLM-POI, a framework that integrates retrieval-augmented generation and self-rectification, achieving substantial accuracy gains across three real-world Foursquare datasets.
Next point-of-interest (POI) recommendation predicts a user's next destination from historical movements. Traditional models require intensive training, while LLMs offer flexible and generalizable zero-shot solutions but often generate generic or geographically irrelevant results due to missing trajectory and spatial context. To address these issues, we propose RALLM-POI, a framework that couples LLMs with retrieval-augmented generation and self-rectification. We first propose a Historical Trajectory Retriever (HTR) that retrieves relevant past trajectories to serve as contextual references, which are then reranked by a Geographical Distance Reranker (GDR) for prioritizing spatially relevant trajectories. Lastly, an Agentic LLM Rectifier (ALR) is designed to refine outputs through self-reflection. Without additional training, RALLM-POI achieves substantial accuracy gains across three real-world Foursquare datasets, outperforming both conventional and LLM-based baselines. Code is released at https://github.com/LKRcrocodile/RALLM-POI.