2026-09-19T20:45:26Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1538942024-03-22T03:53:51Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Tenenbaum, Joshua
Wing, Shannon P.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2024-03-21T19:14:14Z
2024-03-21T19:14:14Z
2024-02
2024-03-04T16:38:09.190Z
https://hdl.handle.net/1721.1/153894
The goal to build a safe Artificial General Intelligence requires an advancement beyond any single human being’s moral capacity. For the same reason why we desire democracy, a moral AGI will need to be able to represent a wide array of perspectives accurately.
While there has been a lot of work to push AI towards correctly answering unanimously agreed upon moral questions, we will take a different approach and ask: What do we do for the space where there is no correct answer, but perhaps multiple? Where there are better and worse arguments? We will investigate one complex moral question, where the empirical human data strays from unanimous agreement, evaluate chatGPT’s success, and build towards a neuro-symbolic framework to improve upon this baseline. By investigating one problem in depth, we hope to uncover nuances, intricacies, and details that might be overlooked in a broader exploration. Our insights intend to spark curiosity, rather than provide answers.
M.Eng.
Massachusetts Institute of Technology
Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)
Copyright retained by author(s)
https://creativecommons.org/licenses/by-nc-nd/4.0/
Towards a neuro-symbolic approach to moral judgment
Thesis
application/pdf
Master
Master of Engineering in Electrical Engineering and Computer Science
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="414ee180-1629-4bfa-b3e6-30126baa9860">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Towards a neuro-symbolic approach to moral judgment</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2024-02</PublicationDate>
<Authors>
<Author>
<DisplayName>Wing, Shannon P.</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>https://creativecommons.org/licenses/by-nc-nd/4.0/</License>
<Abstract>The goal to build a safe Artificial General Intelligence requires an advancement beyond any single human being’s moral capacity. For the same reason why we desire democracy, a moral AGI will need to be able to represent a wide array of perspectives accurately.
While there has been a lot of work to push AI towards correctly answering unanimously agreed upon moral questions, we will take a different approach and ask: What do we do for the space where there is no correct answer, but perhaps multiple? Where there are better and worse arguments? We will investigate one complex moral question, where the empirical human data strays from unanimous agreement, evaluate chatGPT’s success, and build towards a neuro-symbolic framework to improve upon this baseline. By investigating one problem in depth, we hope to uncover nuances, intricacies, and details that might be overlooked in a broader exploration. Our insights intend to spark curiosity, rather than provide answers.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>