Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application
It addresses the problem of high computational demands for LLMs, benefiting researchers and practitioners in resource-constrained environments, but is incremental as it synthesizes existing work.
This survey tackles the challenge of compressing large language models (LLMs) for efficient deployment by reviewing knowledge distillation methods, evaluating their performance, and discussing applications, without presenting new experimental results.
Large Language Models (LLMs) have showcased exceptional capabilities in various domains, attracting significant interest from both academia and industry. Despite their impressive performance, the substantial size and computational demands of LLMs pose considerable challenges for practical deployment, particularly in environments with limited resources. The endeavor to compress language models while maintaining their accuracy has become a focal point of research. Among the various methods, knowledge distillation has emerged as an effective technique to enhance inference speed without greatly compromising performance. This paper presents a thorough survey from three aspects: method, evaluation, and application, exploring knowledge distillation techniques tailored specifically for LLMs. Specifically, we divide the methods into white-box KD and black-box KD to better illustrate their differences. Furthermore, we also explored the evaluation tasks and distillation effects between different distillation methods, and proposed directions for future research. Through in-depth understanding of the latest advancements and practical applications, this survey provides valuable resources for researchers, paving the way for sustained progress in this field.