Is Knowledge Distillation Actually Greener? A Case Study in Machine Translation
This work evaluates representative KD methods both on bespoke MT models and LLMs, by considering both translation quality and computational cost, using the Machine Learning Life Cycle Assessment tool, which accounts for costs throughout the KD model life cycle.
Joseph Attieh, Timothee Mickus, Anne-Laure Ligozat et al.
· 0 citations