# Where to Move Next: Zero-shot Generalization of LLMs for Next POI Recommendation

arXiv: https://arxiv.org/abs/2404.01855 · HTML: https://mlsanity.com/paper/2404.01855/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 34 references that are in the map.
- First posted on arXiv 2 Apr 2024.

## Builds on (most cited first, 23 of 23)

- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [A Survey on Large Language Models for Recommendation](https://mlsanity.com/paper/2305.19860/) (2023)
- [Language Models Represent Space and Time](https://mlsanity.com/paper/2310.02207/) (2023)
- [Large Language Models are Zero-Shot Rankers for Recommender Systems](https://mlsanity.com/paper/2305.08845/) (2023)
- [Is ChatGPT a Good Recommender? A Preliminary Study](https://mlsanity.com/paper/2304.10149/) (2023)
- [Recommender Systems in the Era of Large Language Models (LLMs)](https://mlsanity.com/paper/2307.02046/) (2023)
- [Uncovering ChatGPT's Capabilities in Recommender Systems](https://mlsanity.com/paper/2305.02182/) (2023)
- [How Can Recommender Systems Benefit from Large Language Models: A Survey](https://mlsanity.com/paper/2306.05817/) (2023)
- [GPT4Rec: A Generative Framework for Personalized Recommendation and User Interests Interpretation](https://mlsanity.com/paper/2304.03879/) (2023)
- [Where Would I Go Next? Large Language Models as Human Mobility Predictors](https://mlsanity.com/paper/2308.15197/) (2023)
- [On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligence](https://mlsanity.com/paper/2304.06798/) (2023)
- [Leveraging Large Language Models for Sequential Recommendation](https://mlsanity.com/paper/2309.09261/) (2023)
- [K2: A Foundation Language Model for Geoscience Knowledge Understanding and Utilization](https://mlsanity.com/paper/2306.05064/) (2023)
- [GPT4GEO: How a Language Model Sees the World's Geography](https://mlsanity.com/paper/2306.00020/) (2023)
- [GeoLLM: Extracting Geospatial Knowledge from Large Language Models](https://mlsanity.com/paper/2310.06213/) (2023)
- [GETNext: Trajectory Flow Map Enhanced Transformer for Next POI Recommendation](https://mlsanity.com/paper/2303.04741/) (2023)
- [Zero-Shot Next-Item Recommendation using Large Pretrained Language Models](https://mlsanity.com/paper/2304.03153/) (2023)
- [Autonomous GIS: the next-generation AI-powered GIS](https://mlsanity.com/paper/2305.06453/) (2023)
- [GeoGPT: Understanding and Processing Geospatial Tasks through An Autonomous GPT](https://mlsanity.com/paper/2307.07930/) (2023)
- [Exploring Large Language Models for Human Mobility Prediction under Public Events](https://mlsanity.com/paper/2311.17351/) (2023)
- [Large Language Models for Spatial Trajectory Patterns Mining](https://mlsanity.com/paper/2310.04942/) (2023)
- [Point-of-Interest Recommender Systems based on Location-Based Social Networks: A Survey from an Experimental Perspective](https://mlsanity.com/paper/2106.10069/) (2021)
- [A Multi-Channel Next POI Recommendation Framework with Multi-Granularity Check-in Signals](https://mlsanity.com/paper/2209.00472/) (2022)

## Built on by (most cited first, 17 of 17)

- [Towards Next-Generation LLM-based Recommender Systems: A Survey and Beyond](https://mlsanity.com/paper/2410.19744/) (2024)
- [A Survey of Generative Techniques for Spatial-Temporal Data Mining](https://mlsanity.com/paper/2405.09592/) (2024)
- [Evaluating Large Language Models on Spatial Tasks: A Multi-Task Benchmarking Study](https://mlsanity.com/paper/2408.14438/) (2024)
- [A Survey on Point-of-Interest Recommendation: Models, Architectures, and Security](https://mlsanity.com/paper/2410.02191/) (2024)
- [MAS4POI: a Multi-Agents Collaboration System for Next POI Recommendation](https://mlsanity.com/paper/2409.13700/) (2024)
- [ELLMob: Event-Driven Human Mobility Generation with Self-Aligned LLM Framework](https://mlsanity.com/paper/2603.07946/) (2026)
- [Massive-STEPS: Massive Semantic Trajectories for Understanding POI Check-ins -- Dataset and Benchmarks](https://mlsanity.com/paper/2505.11239/) (2025)
- [On the Performance of LLMs for Real Estate Appraisal](https://mlsanity.com/paper/2506.11812/) (2025)
- [RALLM-POI: Retrieval-Augmented LLM for Zero-shot Next POI Recommendation with Geographical Reranking](https://mlsanity.com/paper/2509.17066/) (2025)
- [Geospatial Mechanistic Interpretability of Large Language Models](https://mlsanity.com/paper/2505.03368/) (2025)
- [Geography-Aware Large Language Models for Next POI Recommendation](https://mlsanity.com/paper/2505.13526/) (2025)
- [Refine-POI: Reinforcement Fine-Tuned Large Language Models for Next Point-of-Interest Recommendation](https://mlsanity.com/paper/2506.21599/) (2025)
- [ARMove: Learning to Predict Human Mobility through Agentic Reasoning](https://mlsanity.com/paper/2604.17419/) (2026)
- [A Foundational Individual Mobility Prediction Model based on Open-Source Large Language Models](https://mlsanity.com/paper/2503.16553/) (2025)
- [STRelay: A Universal Spatio-Temporal Relaying Framework for Location Prediction over Human Trajectory Data](https://mlsanity.com/paper/2508.16620/) (2025)
- [A Comparative Study of Demonstration Selection for Practical Large Language Models-based Next POI Prediction](https://mlsanity.com/paper/2604.06207/) (2026)
- [Enhancing Human Mobility Prediction with Spatially Aware LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2609.14227/) (2026)

## Abstract (arXiv)

Next Point-of-interest (POI) recommendation provides valuable suggestions for users to explore their surrounding environment. Existing studies rely on building recommendation models from large-scale users' check-in data, which is task-specific and needs extensive computational resources. Recently, the pretrained large language models (LLMs) have achieved significant advancements in various NLP tasks and have also been investigated for recommendation scenarios. However, the generalization abilities of LLMs still are unexplored to address the next POI recommendations, where users' geographical movement patterns should be extracted. Although there are studies that leverage LLMs for next-item recommendations, they fail to consider the geographical influence and sequential transitions. Hence, they cannot effectively solve the next POI recommendation task. To this end, we design novel prompting strategies and conduct empirical studies to assess the capability of LLMs, e.g., ChatGPT, for predicting a user's next check-in. Specifically, we consider several essential factors in human movement behaviors, including user geographical preference, spatial distance, and sequential transitions, and formulate the recommendation task as a ranking problem. Through extensive experiments on two widely used real-world datasets, we derive several key findings. Empirical evaluations demonstrate that LLMs have promising zero-shot recommendation abilities and can provide accurate and reasonable predictions. We also reveal that LLMs cannot accurately comprehend geographical context information and are sensitive to the order of presentation of candidate POIs, which shows the limitations of LLMs and necessitates further research on robust human mobility reasoning mechanisms.