Preference-grounded Token-level Guidance for Language Model Fine-tuning Shentao Yang

Oct-8-2025, 15:51:52 GMT–Neural Information Processing Systems

Aligning language models (LMs) with preferences is an important problem in natural language generation.

arxiv preprint arxiv, machine learning, reinforcement learning, (17 more...)

Neural Information Processing Systems

Oct-8-2025, 15:51:52 GMT

Conferences PDF

Country:
- South America > Chile
  - Santiago Metropolitan Region > Santiago Province > Santiago (0.04)
- North America > United States
  - Texas > Travis County
    - Austin (0.04)
  - Michigan > Washtenaw County
    - Ann Arbor (0.04)
- Europe > Spain
  - Catalonia > Barcelona Province > Barcelona (0.04)
- Asia
  - South Korea (0.04)
  - China > Guangxi Province
    - Nanning (0.04)

Genre:
- Workflow (0.67)
- Research Report (0.46)

Industry:
- Education (0.67)

Technology:
- Information Technology > Artificial Intelligence
  - Natural Language (1.00)
  - Machine Learning
    - Neural Networks > Deep Learning (0.93)
    - Reinforcement Learning (0.69)