all AI news
Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models
April 4, 2024, 4:47 a.m. | Taiqiang Wu, Chaofan Tao, Jiahao Wang, Zhe Zhao, Ngai Wong
cs.CL updates on arXiv.org arxiv.org
Abstract: Kullback-Leiber divergence has been widely used in Knowledge Distillation (KD) to compress Large Language Models (LLMs). Contrary to prior assertions that reverse Kullback-Leibler (RKL) divergence is mode-seeking and thus preferable over the mean-seeking forward Kullback-Leibler (FKL) divergence, this study empirically and theoretically demonstrates that neither mode-seeking nor mean-seeking properties manifest in KD for LLMs. Instead, RKL and FKL are found to share the same optimization objective and both converge after a sufficient number of epochs. …
abstract arxiv cs.ai cs.cl distillation divergence knowledge language language models large language large language models llms mean prior study type
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
ML/AI Engineer / NLP Expert - Custom LLM Development (x/f/m)
@ HelloBetter | Remote
Doctoral Researcher (m/f/div) in Automated Processing of Bioimages
@ Leibniz Institute for Natural Product Research and Infection Biology (Leibniz-HKI) | Jena
Seeking Developers and Engineers for AI T-Shirt Generator Project
@ Chevon Hicks | Remote
Global Clinical Data Manager
@ Warner Bros. Discovery | CRI - San Jose - San Jose (City Place)
Global Clinical Data Manager
@ Warner Bros. Discovery | COL - Cundinamarca - Bogotá (Colpatria)
Ingénieur Data Manager / Pau
@ Capgemini | Paris, FR