AI-Assisted Outcome Engineering for Mapping Natural Language to Radar Configuration Files
This paper shows how to use Large Language Models (LLMs) and DSPy prompt engineering to bridge the gap between expert knowledge and user natural language inputs. This approach improves radar system usability by leveraging the DSPy ReAct module and MIPROv2 prompt optimization to facilitate the dynamic generation of radar technical parameters.
Authors
- Eric C. Larson (ORCID: https://orcid.org/0000-0001-6040-868X)
- Darrell L. Young
- Mitchell A. Thornton (ORCID: https://orcid.org/0000-0003-3559-9511)
Institutions
- Southern Methodist University (US)
Publication Details
- Published
- 2025-04-11
- DOI
- https://doi.org/10.1109/dcas65331.2025.11045499
- Primary Topic
- Engineering and Test Systems
- Type
- article
- Field-Weighted Citation Impact
- 0.00