# A Comparative Study of Demonstration Selection for Practical Large Language Models-based Next POI Prediction

arXiv: https://arxiv.org/abs/2604.06207 · HTML: https://mlsanity.com/paper/2604.06207/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 25 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Builds on (most cited first, 13 of 13)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [A Survey on Large Language Models for Recommendation](https://mlsanity.com/paper/2305.19860/) (2023)
- [Uncovering ChatGPT's Capabilities in Recommender Systems](https://mlsanity.com/paper/2305.02182/) (2023)
- [STAN: Spatio-Temporal Attention Network for Next Location Recommendation](https://mlsanity.com/paper/2102.04095/) (2021)
- [Where Would I Go Next? Large Language Models as Human Mobility Predictors](https://mlsanity.com/paper/2308.15197/) (2023)
- [GETNext: Trajectory Flow Map Enhanced Transformer for Next POI Recommendation](https://mlsanity.com/paper/2303.04741/) (2023)
- [Revisiting Demonstration Selection Strategies in In-Context Learning](https://mlsanity.com/paper/2401.12087/) (2024)
- [Zero-Shot Next-Item Recommendation using Large Pretrained Language Models](https://mlsanity.com/paper/2304.03153/) (2023)
- [Large Language Models for Next Point-of-Interest Recommendation](https://mlsanity.com/paper/2404.17591/) (2024)
- [Where to Move Next: Zero-shot Generalization of LLMs for Next POI Recommendation](https://mlsanity.com/paper/2404.01855/) (2024)
- [The Whole is Better than the Sum: Using Aggregated Demonstrations in In-Context Learning for Sequential Recommendation](https://mlsanity.com/paper/2403.10135/) (2024)
- [Prompting for Numerical Sequences: A Case Study on Market Comment Generation](https://mlsanity.com/paper/2404.02466/) (2024)

## Abstract (arXiv)

This paper investigates demonstration selection strategies for predicting a user's next point-of-interest (POI) using large language models (LLMs), aiming to accurately forecast a user's subsequent location based on historical check-in data. While in-context learning (ICL) with LLMs has recently gained attention as a promising alternative to traditional supervised approaches, the effectiveness of ICL significantly depends on the selected demonstration. Although previous studies have examined methods such as random selection, embedding-based selection, and task-specific selection, there remains a lack of comprehensive comparative analysis among these strategies. To bridge this gap and clarify the best practices for real-world applications, we comprehensively evaluate existing demonstration selection methods alongside simpler heuristic approaches such as geographical proximity, temporal ordering, and sequential patterns. Extensive experiments conducted on three real-world datasets indicate that these heuristic methods consistently outperform more complex and computationally demanding embedding-based methods, both in terms of computational cost and prediction accuracy. Notably, in certain scenarios, LLMs using demonstrations selected by these simpler heuristic methods even outperform existing fine-tuned models, without requiring further training. Our source code is available at: https://github.com/ryonsd/DS-LLM4POI.