Full-Stack Domain Enhancement for Combustion LLMs: Construction and Optimization
This work addresses the need for reliable scientific reasoning in combustion science, though it is incremental as it adapts existing LLM techniques to a specific domain.
The authors tackled the problem of hallucinations in general-purpose LLMs when applied to combustion science by proposing a full-stack domain-enhanced workflow, resulting in a model that significantly outperforms state-of-the-art general-purpose and retrieval-augmented methods on combustion reasoning tasks.
Large language models (LLMs) in the direction of task adaptation and capability enhancement for professional fields demonstrate significant application potential. Nevertheless, for complex physical systems such as combustion science, general-purpose LLMs often generate severe hallucinations due to insufficient domain knowledge and the inability to adhere to physical conservation laws. To address this issue, we propose the first full-stack domain-enhanced LLM workflow tailored for the field of combustion science, which integrates automated domain corpus construction, incremental pre-training, instruction fine-tuning, and verifiable reward-based reinforcement learning. This workflow ensures that the model truly internalizes physical laws rather than merely learning textual statistical patterns. We also release FlameBench, a standardized evaluation benchmark specifically designed for complex reasoning tasks in combustion science. Experimental results demonstrate that the model developed in this work significantly outperforms state-of-the-art general-purpose closed-source models and traditional retrieval-augmented generation methods on combustion science reasoning tasks. This work lays a solid technical and resource foundation for the subsequent development of domain-specific scientific research agents with reliable scientific reasoning capabilities.