EDT: Improving Large Language Models' Generation by Entropy-based Dynamic Temperature Sampling
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.
Code (1)
Tasks
DiversitySimilar Papers 제목 키워드 기반
Entropic-Time Inference: Self-Organizing Large Language Model Decoding Beyond Attention
Modern large language model (LLM) inference engines optimize throughput and latency under fixed decoding rules, treating generation as a linear progression in token time. We propose a fundamentally different paradigm: en…
Auxiliary-Hyperparameter-Free Sampling: Entropy Equilibrium for Text Generation
Token sampling strategies critically influence text generation quality in large language models (LLMs). However, existing methods introduce additional hyperparameters, requiring extensive tuning and complicating deployme…
Text GenerationBeyond Temperature: Hyperfitting as a Late-Stage Geometric Expansion
Recent work has identified a counterintuitive phenomenon termed "Hyperfitting", where fine-tuning Large Language Models (LLMs) to near-zero training loss on small datasets surprisingly enhances open-ended generation qual…
SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training
Reinforcement learning (RL) is a key paradigm for post-training large language models (LLMs), but the widely used Group Relative Policy Optimization (GRPO) often suffers from entropy collapse: exploration quickly disappe…
Reinforcement LearningExploring Multi-Temperature Strategies for Token- and Rollout-Level Control in RLVR
Reinforcement Learning has demonstrated substantial improvements in the reasoning abilities of Large Language Models (LLMs), exhibiting significant applicability across various domains. Recent research has identified tha…
Reinforcement Learning