Iryna Gurevych, Xiaodan Zhu, Md Imbesat, Hassan Rizvi
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Spatial reasoning is a crucial component of both biological and artificial intelligence. In this work, we present a comprehensive study of the capability of current state-of-the-art large language models (LLMs) on spatial reasoning. To support our study, we created and contribute a novel Spatial Reasoning Characterization (SpaRC) framework and Spatial Reasoning Paths (SpaRP) 1 datasets, to enable an in-depth understanding of the spatial relations and compositions as well as the usefulness of spatial reasoning chains. We found that all the stateof-the-art LLMs do not perform well on the datasets-their performances are consistently low across different setups. The spatial reasoning capability improves substantially as model sizes scale up. Finetuning both large language models (e.g., Llama-2-70B) and smaller ones (e.g., Llama-2-13B) can significantly improve their F1-scores by 7-32 absolute points. We also found that the top proprietary LLMs still significantly outperform their open-source counterparts in topological spatial understanding and reasoning.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2406.04566")
get_code_for_paper("2406.04566")
have("2406.04566")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2406.04566.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2406.04566)
Connect an agent — have() is free.