LocalIntent: Outcome-Specific Structured Generation for Backend-Compatible Smart Building Automation with Local LLMs
This work investigates whether a complete outcome-specific prompting design improves compact-model outputs beyond generic route-then-generate prompting, and achieves higher intent understanding, device identification, and action/parameter correctness than generic two-stage prompting, while clarification/mode correctnes...
Tian-Yang Liu, Jia-Yue Wang, Zhan-Hao Cheng et al.
· 0 citations