Green AI

Beyond FLOPs: Energy-Aware Knowledge Distillation for Sustainable LLMs on Code-Related Tasks
Background: Large Language Models (LLMs) are increasingly being applied to Software Engineering (SE) tasks, achieving high accuracy …
Enrique Barba Roque, Luís Cruz, Annibale Panichella
Preprint
Metamorphic-Based Many-Objective Distillation of LLMs for Code-related Tasks
Knowledge distillation compresses large language models (LLMs) into more compact and efficient versions that achieve similar accuracy …
Annibale Panichella
Preprint