Structured Command Extraction from Air Traffic Control Communications Using Large Language Models
A.M. Mekerishvili (TU Delft - Aerospace Engineering)
Junzi Sun – Mentor (TU Delft - Operations & Environment)
Patrick Jonk – Mentor (Royal Netherlands Aerospace Centre NLR)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Radiotelephony (RT) remains the primary medium for pilot-controller communication, yet extracting structured information from spoken exchanges is challenging. Deep learning approaches often depend on large annotated datasets, limiting use in data-scarce environments. This study evaluates open-source large language models (LLMs) for Structured Information Extraction (SIE) from ATC communications, with applications in assisting or automating pseudo-pilot tasks. We evaluate Llama 3.3 (70B) with baseline prompting and Gemma-3 (4B) with baseline and fine-tuned variants on ~500 utterances from NLR's ATM simulator. Performance is assessed on human transcripts and ASR outputs from Whisper models, with varying prompt contexts. Cross-sector generalization is tested across two ATC sectors. Using manual scoring, Llama 3.3 achieves micro-F1 0.95 on human transcripts and 0.86 on fine-tuned Whisper outputs. While Gemma-3 performed weaker in its baseline form, fine-tuning on a small sample led to notable improvements. Results demonstrate the potential of LLMs for ATC applications without the need for large annotated datasets.