New ANCHOR framework improves LLM-based POI recommendations

Researchers have developed a new framework called ANCHOR to improve next point-of-interest (POI) recommendation systems. This framework addresses the challenge of directly predicting specific POIs using large language models (LLMs) by first estimating category-level mobility intent in a semantic space. ANCHOR then grounds this intent into a candidate set by integrating category anchors, historical visit data, and user preferences, before a reranker selects the final POI. Experiments on real-world datasets demonstrate that ANCHOR outperforms existing traditional, structure-enhanced, and LLM-based recommendation methods. AI

IMPACT This framework could enhance the accuracy and efficiency of location-based services and personalized recommendations.

RANK_REASON The cluster contains an academic paper detailing a new framework for a specific AI task. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• CORE Recommender
• Hugging Face
• large language models
• point-of-interest (POI) recommendation

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →