Can Causal Circuits Enable Efficient Spatial Reasoning for Geoinformatics in Large Language Models?
Computer Modeling in Engineering & Sciences · 2026 · 148 (1) · 1-10
DOI: 10.32604/cmes.2026.083755 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Modeling in Engineering & Sciences, 2026. Verfasst von Sahil Tripathi und 3 weiteren Autor:innen.
Abstract (Originalsprache)
: Spatial reasoning, defined as the ability to infer and compose relations among entities—is fundamental to geoinformatics applications such as spatial querying and map understanding. However, existing works such as Bidirectional Encoder Representations from Transformers (BERT)-based spatial Question Answering (QA) models and neuro-symbolic models rely on dataset-specific patterns, leading to shortcut learning , where reliance on superficial lexical cues rather than true relational understanding. Recent Large Language Models (LLMs)-based works, including fine-tuning and Chain-of-Thought (CoT) prompting, partially alleviate shortcut learning but remain limited by non-causal reasoning , where predictions depend on spurious correlations rather than stable relational structure. To address these limitations, we propose Causal Inference and Reasoning via
Zitieren
APA
Tripathi, S., Kulahara, M., Saudagar, A. K. J., & AlSagri, H. S. (2026). Can Causal Circuits Enable Efficient Spatial Reasoning for Geoinformatics in Large Language Models?. Computer Modeling in Engineering & Sciences, 148(1), 1-10. https://doi.org/10.32604/cmes.2026.083755
Vancouver
Tripathi S, Kulahara M, Saudagar AKJ, AlSagri HS. Can Causal Circuits Enable Efficient Spatial Reasoning for Geoinformatics in Large Language Models?. Computer Modeling in Engineering & Sciences. 2026;148(1):1-10. doi:10.32604/cmes.2026.083755
BibTeX
@article{Tripathi2026,
author = {Tripathi, Sahil and Kulahara, Manaswi and Saudagar, Abdul Khader Jilani and AlSagri, Hatoon S.},
title = {Can Causal Circuits Enable Efficient Spatial Reasoning for Geoinformatics in Large Language Models?},
journal = {Computer Modeling in Engineering & Sciences},
year = {2026},
volume = {148},
number = {1},
pages = {1--10},
doi = {10.32604/cmes.2026.083755}
}
EUVIMED