# EDT: Improving Large Language Models' Generation by Entropy-based Dynamic Temperature Sampling

**Authors:** Shimao Zhang, Yu Bao, Shujian Huang  
**arXiv:** [2403.14541](https://arxiv.org/abs/2403.14541)  
**Date:** 2024-03-21  
**Summary page:** https://www.summarizepaper.com/fr/arxiv-id/2403.14541v2/

## 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 both generation quality and diversity by dynamically selecting the temperature parameter. Additionally, we also show model performance and comprehensive analyses for 4 different generation benchmarks. Our experiments show that EDT significantly outperforms the existing strategies across different tasks.