# POI-Enhancer: An LLM-based Semantic Enhancement Framework for POI Representation Learning

arXiv: https://arxiv.org/abs/2502.10038 · HTML: https://mlsanity.com/paper/2502.10038/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 40 references that are in the map.
- First posted on arXiv 14 Feb 2025.

## Builds on (most cited first, 17 of 17)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [Fast Transformer Decoding: One Write-Head is All You Need](https://mlsanity.com/paper/1911.02150/) (2019)
- [Spatial-Temporal Large Language Model for Traffic Prediction](https://mlsanity.com/paper/2401.10134/) (2024)
- [UrbanCLIP: Learning Text-enhanced Urban Region Profiling with Contrastive Language-Image Pretraining from the Web](https://mlsanity.com/paper/2310.18340/) (2023)
- [Self-supervised Trajectory Representation Learning with Temporal Regularities and Travel Semantics](https://mlsanity.com/paper/2211.09510/) (2022)
- [ControlTraj: Controllable Trajectory Generation with Topology-Constrained Diffusion Model](https://mlsanity.com/paper/2404.15380/) (2024)
- [GeoGPT: Understanding and Processing Geospatial Tasks through An Autonomous GPT](https://mlsanity.com/paper/2307.07930/) (2023)
- [Continuous Trajectory Generation Based on Two-Stage GAN](https://mlsanity.com/paper/2301.07103/) (2023)
- [GATGPT: A Pre-trained Large Language Model with Graph Attention Network for Spatiotemporal Imputation](https://mlsanity.com/paper/2311.14332/) (2023)
- [MLPST: MLP is All You Need for Spatio-Temporal Prediction](https://mlsanity.com/paper/2309.13363/) (2023)
- [BIGCity: A Universal Spatiotemporal Model for Unified Trajectory and Traffic State Data Analysis](https://mlsanity.com/paper/2412.00953/) (2024)
- [Urban Region Representation Learning with Attentive Fusion](https://mlsanity.com/paper/2312.04606/) (2023)
- [Inferring Metapopulation Propagation Network for Intra-city Epidemic Control and Prevention](https://mlsanity.com/paper/1806.08978/) (2018)
- [CD-CNN: A Partially Supervised Cross-Domain Deep Learning Model for Urban Resident Recognition](https://mlsanity.com/paper/1804.09901/) (2018)
- [Investigating the Role of Feed-Forward Networks in Transformers Using Parallel Attention and Feed-Forward Net Design](https://mlsanity.com/paper/2305.13297/) (2023)

## Built on by (most cited first, 10 of 10)

- [MoRA: Mobility as the Backbone for Geospatial Representation Learning at Scale](https://mlsanity.com/paper/2506.01297/) (2025)
- [Mobility-Embedded POIs: Learning What A Place Is and How It Is Used from Human Movement](https://mlsanity.com/paper/2601.21149/) (2026)
- [ICAD-LLM: One-for-All Anomaly Detection via In-Context Learning with Large Language Models](https://mlsanity.com/paper/2512.01672/) (2025)
- [Contextual Attention Modulation: Towards Efficient Multi-Task Adaptation in Large Language Models](https://mlsanity.com/paper/2510.17705/) (2025)
- [Multi-Agent Pointer Transformer: Seq-to-Seq Reinforcement Learning for Multi-Vehicle Dynamic Pickup-Delivery Problems](https://mlsanity.com/paper/2511.17435/) (2025)
- [HieraMix: A Hierarchical MLP-Mixer for Large-Scale Traffic Forecasting](https://mlsanity.com/paper/2512.07854/) (2025)
- [Capturing Context-Aware Route Choice Semantics for Trajectory Representation Learning](https://mlsanity.com/paper/2510.14819/) (2025)
- [Spatio-Temporal Data Enhanced Vision-Language Model for Traffic Scene Understanding](https://mlsanity.com/paper/2511.08978/) (2025)
- [RoSA: Enhancing Parameter-Efficient Fine-Tuning via RoPE-aware Selective Adaptation in Large Language Models](https://mlsanity.com/paper/2511.21733/) (2025)
- [NARA: Anchor-Conditioned Representation Learning for Heterogeneous Vector Geoentities](https://mlsanity.com/paper/2605.12276/) (2026)

## Abstract (arXiv)

POI representation learning plays a crucial role in handling tasks related to user mobility data. Recent studies have shown that enriching POI representations with multimodal information can significantly enhance their task performance. Previously, the textual information incorporated into POI representations typically involved only POI categories or check-in content, leading to relatively weak textual features in existing methods. In contrast, large language models (LLMs) trained on extensive text data have been found to possess rich textual knowledge. However leveraging such knowledge to enhance POI representation learning presents two key challenges: first, how to extract POI-related knowledge from LLMs effectively, and second, how to integrate the extracted information to enhance POI representations. To address these challenges, we propose POI-Enhancer, a portable framework that leverages LLMs to improve POI representations produced by classic POI learning models. We first design three specialized prompts to extract semantic information from LLMs efficiently. Then, the Dual Feature Alignment module enhances the quality of the extracted information, while the Semantic Feature Fusion module preserves its integrity. The Cross Attention Fusion module then fully adaptively integrates such high-quality information into POI representations and Multi-View Contrastive Learning further injects human-understandable semantic information into these representations. Extensive experiments on three real-world datasets demonstrate the effectiveness of our framework, showing significant improvements across all baseline representations.