zgao3186
Abstract
Entropy minimization with one sample and minimal optimization achieves significant performance improvements for large language models.
We trained 13,440 large language models and found that entropy minimization requires only a single unlabeled data and 10 steps optimization to achieve performance improvements comparable to or even greater than those obtained using thousands of data and carefully designed rewards in rule-based reinforcement learning. This striking result may prompt a rethinking of post-training paradigms for large language models. Our code is avaliable at https://github.com/zitian-gao/one-shot-em.
Community
We trained 13,440 large language models and found that entropy minimization requires only a single unlabeled data and 10 steps optimization to achieve performance improvements comparable to or even greater than those obtained using thousands of data and carefully designed rewards in rule-based reinforcement learning. This striking result may prompt a rethinking of post-training paradigms for large language models. Our code is avaliable at https://github.com/zitian-gao/one-shot-em.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning (2025)
- Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization (2025)
- TTRL: Test-Time Reinforcement Learning (2025)
- Maximizing Confidence Alone Improves Reasoning (2025)
- Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement (2025)
- Behavior Injection: Preparing Language Models for Reinforcement Learning (2025)
- RL in Name Only? Analyzing the Structural Assumptions in RL post-training for LLMs (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 1
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper