Helios: A Foundational Language Model for Smart Energy Knowledge Reasoning and Application
This addresses the need for precise engineering-aligned inference in smart energy systems, which is crucial for carbon neutrality efforts, but it is incremental as it adapts existing LLM methods to a specific domain.
The paper tackles the problem of general-purpose LLMs lacking domain knowledge and physical-constraint awareness for smart energy systems by introducing Helios, a tailored large language model, and shows that it significantly enhances domain knowledge mastery, task execution accuracy, and alignment with human preferences.
In the global drive toward carbon neutrality, deeply coordinated smart energy systems underpin industrial transformation. However, the interdisciplinary, fragmented, and fast-evolving expertise in this domain prevents general-purpose LLMs, which lack domain knowledge and physical-constraint awareness, from delivering precise engineering-aligned inference and generation. To address these challenges, we introduce Helios, a large language model tailored to the smart energy domain, together with a comprehensive suite of resources to advance LLM research in this field. Specifically, we develop Enersys, a multi-agent collaborative framework for end-to-end dataset construction, through which we produce: (1) a smart energy knowledge base, EnerBase, to enrich the model's foundational expertise; (2) an instruction fine-tuning dataset, EnerInstruct, to strengthen performance on domain-specific downstream tasks; and (3) an RLHF dataset, EnerReinforce, to align the model with human preferences and industry standards. Leveraging these resources, Helios undergoes large-scale pretraining, SFT, and RLHF. We also release EnerBench, a benchmark for evaluating LLMs in smart energy scenarios, and demonstrate that our approach significantly enhances domain knowledge mastery, task execution accuracy, and alignment with human preferences.