Monday - December 23, 2024
MIT: Study - Some Language Reward Models Exhibit Political Bias
December 12, 2024
CAMBRIDGE, Massachusetts, Dec. 12 (TNSres) -- The Massachusetts Institute of Technology issued the following news on Dec. 10, 2024:

* * *

Research from the MIT Center for Constructive Communication finds this effect occurs even when reward models are trained on factual data.

* * *

By Ellen Hoffman, Center for Constructive Communication

Large language models (LLMs) that drive generative artificial intelligence apps, such as ChatGPT, . . .

Targeted News Service Document Request Form

This document is available to you by e-mail if you complete the form below with relevant information. There may be a fee for this article or ongoing service of similar materials. We will be in touch shortly.

Name:
What's your
Affiliation
Government Newspaper / Media Business
Public Policy Individual / Student Educators
Email:
Phone:
Organization, if any:
State/Country you are in:
Additonal questions
or comments:

Click here for more information about our products

Click here for more information about our products