Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.05846 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911111864909824 |
|---|---|
| author | Marcelyn, Steeve Cuthbert Gao, Yucen Zhang, Yuzhe Gao, Xiaofeng |
| author_facet | Marcelyn, Steeve Cuthbert Gao, Yucen Zhang, Yuzhe Gao, Xiaofeng |
| contents | Path recommendation (PR) aims to generate travel paths that are customized to a user's specific preferences and constraints. Conventional approaches often employ explicit optimization objectives or specialized machine learning architectures; however, these methods typically exhibit limited flexibility and generalizability, necessitating costly retraining to accommodate new scenarios. This paper introduces an alternative paradigm that conceptualizes PR as a natural language generation task. We present PathGPT, a retrieval-augmented large language model (LLM) system that leverages historical trajectory data and natural language user constraints to generate plausible paths. The proposed methodology first converts raw trajectory data into a human-interpretable textual format, which is then stored in a database. Subsequently, a hybrid retrieval system extracts path-specific context from this database to inform a pretrained LLM. The primary contribution of this work is a novel framework that demonstrates how integrating established information retrieval and generative model components can enable adaptive, zero-shot path generation across diverse scenarios. Extensive experiments on large-scale trajectory datasets indicate that PathGPT's performance is competitive with specialized, learning-based methods, underscoring its potential as a flexible and generalizable path generation system that avoids the need for retraining inherent in previous data-driven models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_05846 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PathGPT: Reframing Path Recommendation as a Natural Language Generation Task with Retrieval-Augmented Language Models Marcelyn, Steeve Cuthbert Gao, Yucen Zhang, Yuzhe Gao, Xiaofeng Information Retrieval Artificial Intelligence Machine Learning Path recommendation (PR) aims to generate travel paths that are customized to a user's specific preferences and constraints. Conventional approaches often employ explicit optimization objectives or specialized machine learning architectures; however, these methods typically exhibit limited flexibility and generalizability, necessitating costly retraining to accommodate new scenarios. This paper introduces an alternative paradigm that conceptualizes PR as a natural language generation task. We present PathGPT, a retrieval-augmented large language model (LLM) system that leverages historical trajectory data and natural language user constraints to generate plausible paths. The proposed methodology first converts raw trajectory data into a human-interpretable textual format, which is then stored in a database. Subsequently, a hybrid retrieval system extracts path-specific context from this database to inform a pretrained LLM. The primary contribution of this work is a novel framework that demonstrates how integrating established information retrieval and generative model components can enable adaptive, zero-shot path generation across diverse scenarios. Extensive experiments on large-scale trajectory datasets indicate that PathGPT's performance is competitive with specialized, learning-based methods, underscoring its potential as a flexible and generalizable path generation system that avoids the need for retraining inherent in previous data-driven models. |
| title | PathGPT: Reframing Path Recommendation as a Natural Language Generation Task with Retrieval-Augmented Language Models |
| topic | Information Retrieval Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2504.05846 |