all AI news
EDT: Improving Large Language Models' Generation by Entropy-based Dynamic Temperature Sampling
March 22, 2024, 4:48 a.m. | Shimao Zhang, Yu Bao, Shujian Huang
cs.CL updates on arXiv.org arxiv.org
Abstract: Recently, Large Language Models (LLMs) have demonstrated outstanding performance across a wide range of downstream language tasks. Temperature sampling is a commonly used decoding strategy for LLMs' generation process. However, a fixed temperature parameter is used in most cases, which may not always be an optimal choice for balancing generation quality and diversity. In this paper, we propose an effective Entropy-based Dynamic Temperature (EDT) Sampling method, to achieve a more balanced performance in terms of …
abstract arxiv cases cs.cl decoding dynamic entropy however improving language language models large language large language models llms performance process sampling strategy tasks type
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Data Engineer - Takealot Group (Takealot.com | Superbalist.com | Mr D Food)
@ takealot.com | Cape Town