Cohn, A.G. orcid.org/0000-0002-7652-8907 and Blackwell, R.E. (2024) Evaluating the Ability of Large Language Models to Reason about Cardinal Directions. [Preprint - arXiv CoRR]
Abstract
We investigate the abilities of a representative set of Large language Models (LLMs) to reason about cardinal directions (CDs). To do so, we create two datasets: the first, co-created with ChatGPT, focuses largely on recall of world knowledge about CDs; the second is generated from a set of templates, comprehensively testing an LLM's ability to determine the correct CD given a particular scenario. The templates allow for a number of degrees of variation such as means of locomotion of the agent involved, and whether set in the first , second or third person. Even with a temperature setting of zero, Our experiments show that although LLMs are able to perform well in the simpler dataset, in the second more complex dataset no LLM is able to reliably determine the correct CD, even with a temperature setting of zero.
Metadata
Item Type: | Preprint |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © Anthony G Cohn and Robert E Blackwell; licensed under Creative Commons License CC-BY 4.0 |
Keywords: | Large Language Models, Spatial Reasoning, Cardinal Directions |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Computing (Leeds) > Artificial Intelligence The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Computing (Leeds) |
Funding Information: | Funder Grant number Alan Turing Institute Not Known ESRC (Economic and Social Research Council) ES/W003473/1 Foreign Commonwealth and Development Office Not Known |
Depositing User: | Symplectic Publications |
Date Deposited: | 14 Aug 2024 11:07 |
Last Modified: | 14 Aug 2024 11:07 |
Identification Number: | 10.48550/arXiv.2406.16528 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:216122 |