Aligner: Efficient Alignment by Learning to Correct

Oct-10-2025, 12:16:46 GMT–Neural Information Processing Systems

Aligner can be applied to any powerful, large-scale upstream models. Moreover, it can even iteratively bootstrap the upstream models using corrected responses as synthetic human preference data, breaking through the model's performance ceiling.

large language model, machine learning, natural language, (20 more...)

Neural Information Processing Systems

Oct-10-2025, 12:16:46 GMT

Conferences PDF

Add feedback

Country:
- Asia
  - China > Beijing
    - Beijing (0.04)
  - Japan > Honshū
    - Kantō > Tokyo Metropolis Prefecture > Tokyo (0.04)
  - Russia (0.04)
- Europe
  - Latvia > Lubāna Municipality
    - Lubāna (0.04)
  - Russia (0.04)

Genre:
- Research Report
  - Experimental Study (1.00)
  - New Finding (0.93)

Industry:
- Education (0.67)
- Information Technology > Security & Privacy (0.93)
- Law (1.00)

Technology:
- Information Technology
  - Artificial Intelligence
    - Machine Learning > Neural Networks
      - Deep Learning (1.00)
    - Natural Language
      - Chatbot (0.98)
      - Large Language Model (1.00)
    - Representation & Reasoning (1.00)
  - Security & Privacy (0.93)

Duplicate Docs Excel Report

Title
a51a74b2d71387dc71cc29181b5519bb-Paper-Conference.pdf

Similar Docs Excel Report more

Title	Similarity	Source
None found