POTracker: Optimizing Large Language Models for Standard-Compliant Power Outage Report Generation
2026-06-22 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors worked on improving how large language models generate power outage reports, which have to follow strict formatting rules to be useful. They created POTracker, a special version of a language model fine-tuned with a loss function that checks both the text and its structure. Their approach outperformed other methods in making accurate, properly formatted reports. They also had experts review the reports, who gave them good quality scores. This helps make sure that automated reports meet energy industry standards.
large language modelsfine-tuningloss functionpower outage reportsstructural accuracytext generationJSONXMLutility interoperabilitydomain-specific generation
Authors
Hung Phan, Aniroop Naladala, Dubey Avanindra, Supryia Chinthavali, Lunga Dalton, Ali Jannesari
Abstract
Recent large language models (LLMs) are good at general text generation, but it is still hard to use them for domain-specific data generation because the output must follow strict formatting and structural rules. Unlike open-ended tasks such as question answering or translation, domain-specific generation must be both semantically correct and compliant with existing guidelines and standards. In this work, we study the nationwide interoperability problem of utility power outage reports in the United States. In practice, outage reports need to be machine-readable (e.g., JSON or XML) and must strictly follow requirements from energy-sector regulatory bodies. To address this problem, we propose POTracker, an optimized LLM for power outage report generation. We fine-tune Qwen2.5-7B-Instruct using our proposed objective. The key contribution is a new loss function, POTrackerLoss, that considers both textual similarity and structural (tag) similarity between the generated report and the ground-truth report. We evaluate POTracker on a dataset of 1,000 power outage reports and compare it with five well-known fine-tuning methods and one rule-based XML conversion method. Results show that POTracker outperforms other fine-tuning approaches, improving overall accuracy by up to 51% and reaching 86.47% structural accuracy for generated power outage reports. In addition, we conduct a human study to assess the quality of the ground-truth standard reports, where domain experts assign the generated labels an average score of 4.03 on a 0--5 scale.