paper-with-me

홈 › Papers

Auxiliary-Hyperparameter-Free Sampling: Entropy Equilibrium for Text Generation

2025-11-30 · Xiaodong Cai, Hai Lin, Shaoxiong Zhan, Weiqi Luo, Hong-Gee Kim, Hongyan Hao, Yu Yang, Hai-Tao Zheng arxiv

Token sampling strategies critically influence text generation quality in large language models (LLMs). However, existing methods introduce additional hyperparameters, requiring extensive tuning and complicating deployment. We present Entropy Equilibrium Sampling (EES), an auxiliary hyperparameter-free approach inspired by information theory that can dynamically adjust candidate sets by balancing normalized entropy with probability mass. We evaluate EES on both reasoning and generation tasks across a range of model architectures. Our results show that EES consistently performs well across temperature settings, delivering competitive accuracy and coherence while maintaining diversity. By eliminating the need for hyperparameter tuning, EES greatly simplifies deployment while improving performance. Code is available at https://github.com/shuanncai/EES

📄 PDF Abstract BibTeX arXiv:2512.00789

Code (0)

등록된 구현이 없습니다.

Tasks

Text Generation

Similar Papers 제목 키워드 기반

BITS for GAPS: Bayesian Information-Theoretic Sampling for hierarchical GAussian Process Surrogates

2025-11-20 · Kyla D. Jones, Alexander W. Dowling arxiv

We introduce Bayesian Information-Theoretic Sampling for hierarchical GAussian Process Surrogates (BITS for GAPS), a framework enabling information-theoretic experimental design of Gaussian process-based surrogate models…

Scale Equalization for Multi-Level Feature Fusion

2024-02-02 · Bum Jun Kim, Sang Woo Kim

Deep neural networks have exhibited remarkable performance in a variety of computer vision fields, especially in semantic segmentation tasks. Their success is often attributed to multi-level feature fusion, which enables…

DecoderSemantic Segmentation

Entropy-Aligned Decoding of LMs for Better Writing and Reasoning

2026-01-05 · Kareem Ahmed, Sameer Singh arxiv

Language models (LMs) are trained on billions of tokens in an attempt to recover the true language distribution. Still, vanilla random sampling from LMs yields low quality generations. Decoding algorithms attempt to rest…

Mathematical Reasoning

Enhanced Diffusion Sampling: Efficient Rare Event Sampling and Free Energy Calculation with Diffusion Models

2026-02-18 · Yu Xie, Ludwig Winkler, Lixin Sun, Sarah Lewis 외 arxiv

The rare-event sampling problem has long been the central limiting factor in molecular dynamics (MD), especially in biomolecular simulation. Recently, diffusion models such as BioEmu have emerged as powerful equilibrium …

SACn: Soft Actor-Critic with n-step Returns

2025-12-15 · Jakub Łyskawa, Jakub Lewandowski, Paweł Wawrzyński arxiv

Soft Actor-Critic (SAC) is widely used in practical applications and is now one of the most relevant off-policy online model-free reinforcement learning (RL) methods. The technique of n-step returns is known to increase …

Reinforcement Learning