Rule Based Rewards for Language Model Safety

Nov-20-2025, 13:37:38 GMT–Neural Information Processing Systems

We propose a novel preference modeling approach that utilizes AI feedback and only requires a small amount of human data.

large language model, machine learning, reinforcement learning, (22 more...)

Neural Information Processing Systems

Nov-20-2025, 13:37:38 GMT

Conferences PDF

Country:
- Europe > France (0.04)

Genre:
- Research Report > Experimental Study (0.46)

Industry:
- Health & Medicine > Therapeutic Area > Psychiatry/Psychology (0.68)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning
    - Neural Networks > Deep Learning (1.00)
    - Reinforcement Learning (0.68)
  - Natural Language
    - Chatbot (1.00)
    - Large Language Model (1.00)
  - Representation & Reasoning (1.00)

Duplicate Docs Excel Report

Title
Rule Based Rewards for Language Model Safety

Similar Docs Excel Report more

Title	Similarity	Source
None found