Fully-funded Ph.D. Positions in Mechanistic Interpretability and Neurosymbolic NN by-design

The project:  <https://aclanthology.org/2025.findings-acl.785/> Position
Paper: MeMo: Towards Language Models with Associative Memory Mechanisms -
ACL Anthology

 

Do YOU have a strong mathematical background, good programming skills,
passion and curiosity, the ability to think out of the box? This is the
Ph.D. Program for YOU:

*	Position 1) Mechanistic Interpretability by-design in
Neural-Network-based Large Language Models: This theme is in the context of
the MeMo project that aims to build alternative ways to build transparent
Large Language Models by explicitly using Associative Memories.
*	Position 2) Injecting Neuro-symbolic Natural Language Processing
Capabilities in Neural-Network-based Large Language Models: This theme is in
the context of the MeMo project that aims to build alternative ways to build
transparent Large Language Models by explicitly using Associative Memories.

The positions will formally open in mid-April 2026 and will start on
November 1st, 2026.

 

If you want to see if you fit the position, take this test
<https://forms.office.com/e/sSCGhP9MgF> Open Fully-funded Ph.D. Positions in
the Data Science Ph.D. School  and book an informal  chat to understand if
the positions fit you.

 

Positions are based in Ph.D. on Data Science at University of Rome Tor
Vergata (Rome, Italy) in the  <https://humancentricart.github.io/>
HumanCentricART Group

_______________________________________________
Corpora mailing list -- [email protected]
https://list.elra.info/mailman3/postorius/lists/corpora.list.elra.info/
To unsubscribe send an email to [email protected]