Multimodal-to-Text Prompt Engineering in Large Language Models Using Feature Embeddings for GNSS Interference Characterization
Manjunath H, Heublein L, Feigl T, Ott F (2026)
Publication Status: Submitted
Publication Type: Unpublished / Preprint
Future Publication Type: Journal article
Publication year: 2026
Publisher: arXiv
DOI: 10.48550/arXiv.2501.05079
Abstract
Large language models (LLMs) are advanced AI systems applied across various domains, including NLP, information retrieval, and recommendation systems. Despite their adaptability and efficiency, LLMs have not been extensively explored for signal processing tasks, particularly in the domain of global navigation satellite system (GNSS) interference monitoring. GNSS interference monitoring is essential to ensure the reliability of vehicle localization on roads, a critical requirement for numerous applications. However, GNSS-based positioning is vulnerable to interference from jamming devices, which can compromise its accuracy. The primary objective is to identify, classify, and mitigate these interferences. Interpreting GNSS snapshots and the associated interferences presents significant challenges due to the inherent complexity, including multipath effects, diverse interference types, varying sensor characteristics, and satellite constellations. In this paper, we extract features from a large GNSS dataset and employ LLaVA to retrieve relevant information from an extensive knowledge base. We employ prompt engineering to interpret the interferences and environmental factors, and utilize t-SNE to analyze the feature embeddings. Our findings demonstrate that the proposed method is capable of visual and logical reasoning within the GNSS context. Furthermore, our pipeline outperforms state-of-the-art machine learning models in interference classification tasks.
Authors with CRIS profile
Involved external institutions
Fraunhofer-Institut für Integrierte Schaltungen (IIS)
Germany (DE)
Fraunhofer-Institut für Integrierte Systeme und Bauelementetechnologie (IISB)
Germany (DE)
Germany (DE)
Fraunhofer-Institut für Integrierte Systeme und Bauelementetechnologie (IISB)
Germany (DE)
How to cite
APA:
Manjunath, H., Heublein, L., Feigl, T., & Ott, F. (2026). Multimodal-to-Text Prompt Engineering in Large Language Models Using Feature Embeddings for GNSS Interference Characterization. (Unpublished, Submitted).
MLA:
Manjunath, Harshith, et al. Multimodal-to-Text Prompt Engineering in Large Language Models Using Feature Embeddings for GNSS Interference Characterization. Unpublished, Submitted. 2026.
BibTeX: Download