TransitLM: Public Transit Routes for Four Chinese Cities

TransitLM is a dataset for public transit route planning in Chinese urban environments, designed to support training and evaluation of language models. The full dataset covers four cities: Beijing, Shanghai, Shenzhen, and Chengdu, and includes coordinates, station sequences, transfer structure, line information, and route data. It was authored by GD-ML and last updated on the Hugging Face platform in May 2026.

Use Cases

• Train language models to generate transit routes based on origin-destination information.
• Evaluate model performance on structured route planning tasks in Chinese cities.
• Analyze public transit network structures and transfer patterns across different urban environments.
• Develop geospatial applications that require detailed station sequences and line information.

Strengths

• Covers four major Chinese cities: Beijing, Shanghai, Shenzhen, and Chengdu.
• Includes multiple data aspects such as coordinates, station sequences, transfer structure, and line information.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment for large-scale training.

Provenance

Source

GD-ML on Hugging Face.

Freshness

Last updated 2026-05-13 08:43:21; freshness should be verified.

Geography

Beijing, Shanghai, Shenzhen, and Chengdu, China.