Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs Rui Y ang 1 Ruomeng Ding 2 Yong Lin
–Neural Information Processing Systems
While previous research has advocated for constraining policy optimization, our study introduces a novel approach to enhance the reward model's
Neural Information Processing Systems
Feb-15-2026, 20:07:43 GMT
- Country:
- Asia > Middle East
- Jordan (0.04)
- North America > United States
- California (0.04)
- Illinois > Champaign County
- Urbana (0.04)
- Tennessee > Davidson County
- Nashville (0.04)
- Asia > Middle East
- Genre:
- Research Report
- Experimental Study (0.93)
- New Finding (1.00)
- Research Report
- Industry:
- Leisure & Entertainment (0.93)
- Media > Music (1.00)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning > Neural Networks
- Deep Learning (0.95)
- Natural Language
- Chatbot (0.93)
- Large Language Model (1.00)
- Representation & Reasoning (1.00)
- Vision (1.00)
- Machine Learning > Neural Networks
- Information Technology > Artificial Intelligence