Abstract
Accurate user-equipment positioning is crucial for the successful deployment of 5G New Radio (NR) networks, particularly in dense urban and vehicular environments where multipath effects and signal blockage frequently compromise GNSS reliability. Building upon the pseudo-signal-word (PSW) paradigm initially developed for low-power wide-area networks, this paper proposes GeoNR-PSW, a novel localization architecture designed for sub-6 GHz (FR1, 2.8 GHz) and mmWave (FR2, 60 GHz) fingerprints from the Raymobtime S007 dataset. GeoNR-PSW encodes 5G channel snapshots into concise PSW sequences and leverages a frozen GPT-2 backbone enhanced by lightweight PSW-Adapters to enable few-shot 3D localization. Despite the limited size of the dataset, the proposed method achieves median localization errors of 5.90 m at FR1 and 3.25 m at FR2. These results highlight the potential of prompt-aligned language models for accurate and scalable 5G positioning with minimal supervision.