Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2510.14702 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911215107702784 |
|---|---|
| author | Zhai, Penglong Li, Jie Di, Fanyi Liu, Yue Yuan, Yifang Huang, Jie Wu, Peng Wang, Sicong Yin, Mingyang Hu, Tingting Xu, Yao Li, Xin |
| author_facet | Zhai, Penglong Li, Jie Di, Fanyi Liu, Yue Yuan, Yifang Huang, Jie Wu, Peng Wang, Sicong Yin, Mingyang Hu, Tingting Xu, Yao Li, Xin |
| contents | The next point-of-interest (POI) recommendation task aims to predict the users' immediate next destinations based on their preferences and historical check-ins, holding significant value in location-based services. Recently, large language models (LLMs) have shown great potential in recommender systems, which treat the next POI prediction in a generative manner. However, these LLMs, pretrained primarily on vast corpora of unstructured text, lack the native understanding of structured geographical entities and sequential mobility patterns required for next POI prediction tasks. Moreover, in industrial-scale POI prediction applications, incorporating world knowledge and alignment of human cognition, such as seasons, weather conditions, holidays, and users' profiles (such as habits, occupation, and preferences), can enhance the user experience while improving recommendation performance. To address these issues, we propose CoAST (Cognitive-Aligned Spatial-Temporal LLMs), a framework employing natural language as an interface, allowing for the incorporation of world knowledge, spatio-temporal trajectory patterns, profiles, and situational information. Specifically, CoAST mainly comprises of 2 stages: (1) Recommendation Knowledge Acquisition through continued pretraining on the enriched spatial-temporal trajectory data of the desensitized users; (2) Cognitive Alignment to align cognitive judgments with human preferences using enriched training data through Supervised Fine-Tuning (SFT) and a subsequent Reinforcement Learning (RL) phase. Extensive offline experiments on various real-world datasets and online experiments deployed in "Guess Where You Go" of AMAP App homepage demonstrate the effectiveness of CoAST. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_14702 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Cognitive-Aligned Spatio-Temporal Large Language Models For Next Point-of-Interest Prediction Zhai, Penglong Li, Jie Di, Fanyi Liu, Yue Yuan, Yifang Huang, Jie Wu, Peng Wang, Sicong Yin, Mingyang Hu, Tingting Xu, Yao Li, Xin Artificial Intelligence The next point-of-interest (POI) recommendation task aims to predict the users' immediate next destinations based on their preferences and historical check-ins, holding significant value in location-based services. Recently, large language models (LLMs) have shown great potential in recommender systems, which treat the next POI prediction in a generative manner. However, these LLMs, pretrained primarily on vast corpora of unstructured text, lack the native understanding of structured geographical entities and sequential mobility patterns required for next POI prediction tasks. Moreover, in industrial-scale POI prediction applications, incorporating world knowledge and alignment of human cognition, such as seasons, weather conditions, holidays, and users' profiles (such as habits, occupation, and preferences), can enhance the user experience while improving recommendation performance. To address these issues, we propose CoAST (Cognitive-Aligned Spatial-Temporal LLMs), a framework employing natural language as an interface, allowing for the incorporation of world knowledge, spatio-temporal trajectory patterns, profiles, and situational information. Specifically, CoAST mainly comprises of 2 stages: (1) Recommendation Knowledge Acquisition through continued pretraining on the enriched spatial-temporal trajectory data of the desensitized users; (2) Cognitive Alignment to align cognitive judgments with human preferences using enriched training data through Supervised Fine-Tuning (SFT) and a subsequent Reinforcement Learning (RL) phase. Extensive offline experiments on various real-world datasets and online experiments deployed in "Guess Where You Go" of AMAP App homepage demonstrate the effectiveness of CoAST. |
| title | Cognitive-Aligned Spatio-Temporal Large Language Models For Next Point-of-Interest Prediction |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2510.14702 |