Large language models are becoming general-purpose tools for engineers and researchers, and they demand careful evaluation.
Why Applications of LLMs for Engineering matters
Understanding how large language models are built, trained and optimised is essential for applying them well. This track covers architectures, efficiency, natural language understanding, ethics and bias, and real applications in industry and research, together with the directions the field is heading.
NLP and machine learning researchers, engineers building LLM-based tools, and practitioners studying fairness, bias and deployment are encouraged to submit.
Topics of interest
- Foundations and Architectures of LLMs
- Training, Efficiency, and Optimization
- LLMs in Natural Language Understanding
- Ethics, Fairness, and Bias in LLMs
- Applications of LLMs in Industry and Research
- Future Directions and Innovations in LLMs
Submit to this track
Choose Track 9: Applications of LLM for Engineering when you upload your paper, abstract or poster in the Microsoft CMT portal. The deadline is November 30, 2026. Accepted and presented full papers will be published in Scopus-indexed proceedings with a unique DOI.