Skip to Main Content

Search

Skip to Search Results
Filter
Close
Author / Creator / Contributor
Subject / Keyword
Departments
Year
to
Collections
Languages
Item type
Supervisors
Author: Hao, Yongchang Subject: Reinforcement learning Departments: Department of Computing Science

  • Discovering Reward Functions for Language Models

    Download

    Fall 2023

    Hao, Yongchang

    Language models are a fundamental component of natural language processing (NLP) systems. Numerous successful deployments of modern artificial intelligence systems are based on language models, including GPT-4 and ChatGPT. In practice, they are often trained with the teacher forcing objective,...

1 - 1 of 1