Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.03424 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915323932835840 |
|---|---|
| author | Schneider, Nicole R Ramachandran, Nandini O'Sullivan, Kent Samet, Hanan |
| author_facet | Schneider, Nicole R Ramachandran, Nandini O'Sullivan, Kent Samet, Hanan |
| contents | Many real world tasks where Large Language Models (LLMs) can be used require spatial reasoning, like Point of Interest (POI) recommendation and itinerary planning. However, on their own LLMs lack reliable spatial reasoning capabilities, especially about distances. To address this problem, we develop a novel approach, DistRAG, that enables an LLM to retrieve relevant spatial information not explicitly learned during training. Our method encodes the geodesic distances between cities and towns in a graph and retrieves a context subgraph relevant to the question. Using this technique, our method enables an LLM to answer distance-based reasoning questions that it otherwise cannot answer. Given the vast array of possible places an LLM could be asked about, DistRAG offers a flexible first step towards providing a rudimentary `world model' to complement the linguistic knowledge held in LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_03424 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DistRAG: Towards Distance-Based Spatial Reasoning in LLMs Schneider, Nicole R Ramachandran, Nandini O'Sullivan, Kent Samet, Hanan Computation and Language Information Retrieval Many real world tasks where Large Language Models (LLMs) can be used require spatial reasoning, like Point of Interest (POI) recommendation and itinerary planning. However, on their own LLMs lack reliable spatial reasoning capabilities, especially about distances. To address this problem, we develop a novel approach, DistRAG, that enables an LLM to retrieve relevant spatial information not explicitly learned during training. Our method encodes the geodesic distances between cities and towns in a graph and retrieves a context subgraph relevant to the question. Using this technique, our method enables an LLM to answer distance-based reasoning questions that it otherwise cannot answer. Given the vast array of possible places an LLM could be asked about, DistRAG offers a flexible first step towards providing a rudimentary `world model' to complement the linguistic knowledge held in LLMs. |
| title | DistRAG: Towards Distance-Based Spatial Reasoning in LLMs |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2506.03424 |