Can AI Make Energy Retrofit Decisions? An Evaluation of Large Language Models
Not on the map. Why?
Abstract (arXiv)
Conventional approaches to building energy retrofit decision making suffer from limited generalizability and low interpretability, hindering adoption in diverse residential contexts. With the growth of Smart and Connected Communities, generative AI, especially large language models (LLMs), may help by processing contextual information and producing practitioner readable recommendations. We evaluate seven LLMs (ChatGPT, DeepSeek, Gemini, Grok, Llama, and Claude) on residential retrofit decisions under two objectives: maximizing CO2 reduction (technical) and minimizing payback period (sociotechnical). Performance is assessed on four dimensions: accuracy, consistency, sensitivity, and reasoning, using a dataset of 400 homes across 49 US states. LLMs generate effective recommendations in many cases, reaching up to 54.5 percent top 1 match and 92.8 percent within top 5 without fine tuning. Performance is stronger for the technical objective, while sociotechnical decisions are limited by economic trade offs and local context. Agreement across models is low, and higher performing models tend to diverge from others. LLMs are sensitive to location and building geometry but less sensitive to technology and occupant behavior. Most models show step by step, engineering style reasoning, but it is often simplified and lacks deeper contextual awareness. Overall, LLMs are promising assistants for energy retrofit decision making, but improvements in accuracy, consistency, and context handling are needed for reliable practice.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 17 of its 59 references that are in the map. First posted on arXiv 8 Sep 2025.
Builds on
17 of 59 references.
References · 17
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
- 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
- 2024A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applicationscited by 431
- 2023Explainability for Large Language Models: A Surveycited by 333
- 2024Does Prompt Formatting Have Any Impact on LLM Performance?cited by 141
- 2024The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performancecited by 100
- 2024Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilitiescited by 69
- 2023Retrieval-augmented Generation to Improve Math Question-Answering: Trade-offs Between Groundedness and Human Preferencecited by 38
- 2024Exploring the Capabilities and Limitations of Large Language Models in the Electric Energy Sectorcited by 30
- 2024Predictions from language models for multiple-choice tasks are not robust under variation of scoring methodscited by 13
- 2024EF-LLM: Energy Forecasting LLM with AI-assisted Automation, Enhanced Sparse Prediction, Hallucination Detectioncited by 6
- 2024Information Re-Organization Improves Reasoning in Large Language Modelscited by 5
5 more
- 2024Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning Taskscited by 5
- 2024Investigating Context Effects in Similarity Judgements in Large Language Modelscited by 3
- 2025Retrieval-Augmented Generation by Evidence Retroactivity in LLMscited by 3
- 2024LuminLab: An AI-Powered Building Retrofit and Energy Modelling Platformcited by 1
- 2024Testing Uncertainty of Large Language Models for Physics Knowledge and Reasoningcited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.