DeepSeek-V3, GPT-4, Phi-4, and LLaMA-3.3 Generate Correct Code for LoRaWAN-Related Engineering Tasks

01/04/2025

This paper investigates the performance of 16 Large Language Models (LLMs) in automating LoRaWAN-related engineering tasks involving optimal placement of drones and received power calculation under progressively complex zero-shot, natural language prompts. The primary research question is whether lightweight, locally executed LLMs can generate correct Python code for these tasks. To assess this, we compared locally run models against state-of-the-art alternatives, such as GPT-4 and DeepSeek-V3, which served as reference points. By extracting and executing the Python functions generated by each model, we evaluated their outputs on a zero-to-five scale. Results show that while DeepSeek-V3 and GPT-4 consistently provided accurate solutions, certain smaller models—particularly Phi-4 and LLaMA-3.3—also demonstrated strong performance, underscoring the viability of lightweight alternatives. Other models exhibited errors stemming from incomplete understanding or syntactic issues. These findings illustrate the potential of LLM-based approaches for specialized engineering applications while highlighting the need for careful model selection, rigorous prompt design, and targeted domain fine-tuning to achieve reliable outcomes.

Autores da comunidade :

• 

  C

  Carlos Miguel da Costa Fernandes

  ist46419

• 

  N

  Nuno Fachada

  ist145239

  Afiliações e fontes

  IST > LARSYS

  Laboratório de Robótica e Sistemas em Engenharia e Ciência

VoR - Versão publicada

MDPI

https://doi.org/10.3390/electronics14071428

Electronics

1428

14

7

2079-9292

10.3390/electronics14071428

computer-and-information-sciences - Ciências da Computação e da Informação

Palavras-chave

• LoRaWan
• Large Language Models
• LLMs
• UAVs
• Drones
• UAV placement
• code generation
• IoT

eng - Inglês

CC-BY - CC-BY