LAMP: A Language Model on the Map
Pasquale Balsebre, Weiming Huang, Gao Cong

TL;DR
LAMP is a fine-tuned language model designed to improve the accuracy of location-specific questions in the geospatial domain by training on city-specific data, enabling better recommendations and understanding of local places.
Contribution
The paper introduces LAMP, a novel framework for fine-tuning language models with city-specific data to enhance spatial understanding and reduce hallucinations in geospatial queries.
Findings
LAMP outperforms general LLMs in retrieving spatial objects.
LAMP demonstrates improved accuracy over GPT-4 in geospatial tasks.
Case study shows LAMP's potential in day planning applications.
Abstract
Large Language Models (LLMs) are poised to play an increasingly important role in our lives, providing assistance across a wide array of tasks. In the geospatial domain, LLMs have demonstrated the ability to answer generic questions, such as identifying a country's capital; nonetheless, their utility is hindered when it comes to answering fine-grained questions about specific places, such as grocery stores or restaurants, which constitute essential aspects of people's everyday lives. This is mainly because the places in our cities haven't been systematically fed into LLMs, so as to understand and memorize them. This study introduces a novel framework for fine-tuning a pre-trained model on city-specific data, to enable it to provide accurate recommendations, while minimizing hallucinations. We share our model, LAMP, and the data used to train it. We conduct experiments to analyze its…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGeographic Information Systems Studies · Semantic Web and Ontologies
MethodsAttention Is All You Need · Absolute Position Encodings · Residual Connection · Dropout · Softmax · Linear Layer · Multi-Head Attention · Position-Wise Feed-Forward Layer · Byte Pair Encoding · Layer Normalization
