Abstract
dc:description.abstractLarge language models (LLMs) have been experiencing a rapid rise in utility, accessibility, and popularity, but there are still many areas in which they can improve. One such area for improvement is their truthfulness. We seek to improve the truthfulness of LLMs by probing their internal representations. We find that a linear probe on the last hidden layer representation is able to improve a model’s accuracy by reducing its confidence in incorrect answers. However, this probe is less effective at perturbing the model to change its behavior and driving the model towards correct answers.
Degree
thesis:*- Name thesis:degree_name
- Master
- Department dc:contributor.department
- Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
- Grantor dc:publisher
- Massachusetts Institute of Technology
- Year dc:date.issued
- 2023
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Liu, Kevin
- Advisors dc:contributor.advisor
-
- Andreas, Jacob
- Hadfield-Menell, Dylan
Rights
dc:rights- Statement dc:rights
-
- In Copyright - Educational Use Permitted
- Copyright retained by author(s)
- Licence dc:rights.uri
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- https://hdl.handle.net/1721.1/151345
- OAI identifier oai:identifier
- oai:dspace.mit.edu:1721.1/151345