A unified foundational framework for knowledge injection and evaluation of Large Language Models in Combustion Science
#Large Language Models #combustion science #knowledge injection #AI evaluation #domain-specific AI #scientific framework #LLM performance
📌 Key Takeaways
- Researchers propose a unified framework for integrating domain knowledge into Large Language Models (LLMs) for combustion science.
- The framework focuses on injecting specialized combustion science knowledge into LLMs to enhance their accuracy and relevance.
- It includes methods for evaluating the performance of LLMs after knowledge injection to ensure reliability in scientific applications.
- The approach aims to bridge the gap between general AI capabilities and domain-specific scientific research needs.
📖 Full Retelling
arXiv:2603.04452v1 Announce Type: cross
Abstract: To advance foundation Large Language Models (LLMs) for combustion science, this study presents the first end-to-end framework for developing domain-specialized models for the combustion community. The framework comprises an AI-ready multimodal knowledge base at the 3.5 billion-token scale, extracted from over 200,000 peer-reviewed articles, 8,000 theses and dissertations, and approximately 400,000 lines of combustion CFD code; a rigorous and lar
🏷️ Themes
AI Integration, Scientific Research
📚 Related People & Topics
Large language model
Type of machine learning model
A large language model (LLM) is a language model trained with self-supervised machine learning on a vast amount of text, designed for natural language processing tasks, especially language generation. The largest and most capable LLMs are generative pre-trained transformers (GPTs) that provide the c...
Entity Intersection Graph
Connections for Large language model:
🌐
Artificial intelligence
3 shared
🌐
Reinforcement learning
3 shared
🌐
Educational technology
2 shared
🌐
Benchmark
2 shared
🏢
OpenAI
2 shared
Mentioned Entities
Original Source
--> Computer Science > Computation and Language arXiv:2603.04452 [Submitted on 27 Feb 2026] Title: A unified foundational framework for knowledge injection and evaluation of Large Language Models in Combustion Science Authors: Zonglin Yang , Runze Mao , Tianhao Wu , Han Li , QingGuo Zhou , Zhi X. Chen View a PDF of the paper titled A unified foundational framework for knowledge injection and evaluation of Large Language Models in Combustion Science, by Zonglin Yang and 5 other authors View PDF HTML Abstract: To advance foundation Large Language Models for combustion science, this study presents the first end-to-end framework for developing domain-specialized models for the combustion community. The framework comprises an AI-ready multimodal knowledge base at the 3.5 billion-token scale, extracted from over 200,000 peer-reviewed articles, 8,000 theses and dissertations, and approximately 400,000 lines of combustion CFD code; a rigorous and largely automated evaluation benchmark (CombustionQA, 436 questions across eight subfields); and a three-stage knowledge-injection pathway that progresses from lightweight retrieval-augmented generation to knowledge-graph-enhanced retrieval and continued pretraining. We first quantitatively validate Stage 1 (naive RAG) and find a hard ceiling: standard RAG accuracy peaks at 60%, far surpassing zero-shot performance (23%) yet well below the theoretical upper bound (87%). We further demonstrate that this stage's performance is severely constrained by context contamination. Consequently, building a domain foundation model requires structured knowledge graphs and continued pretraining (Stages 2 and 3). Comments: 5 figures, 1 table Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2603.04452 [cs.CL] (or arXiv:2603.04452v1 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2603.04452 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Runze Mao [ view email ] [v1] Fri...
Read full article at source