Publications
2026 PESGM

Fine-Tuning LLMs to Generate Economical and Reliable Actions for the Power Grid

M. Chehade, H. Zhu

Accepted to 2026 IEEE Power & Energy Society General Meeting (PESGM), 2026

A fine-tuning framework for language models that generate corrective power-grid actions while balancing cost and reliability.

Paper preview showing the multi-stage LLM adaptation pipeline for PSPS corrective switching
Preview cropped from the paper PDF.

Contribution

What this paper adds

  • Connects LLM fine-tuning with structured grid-action generation.
  • Evaluates action quality through economic and reliability-oriented criteria.
  • Uses power systems as a constrained decision-making testbed for LLMs.