Hypothesis: We can fine tune a model to tell us when it thinks it’s hallucinating How?: Create a dataset that we use to fine tune a model to output a hallucination token, or in other words a hallutoken, when it thinks it’s hallucinating.
-
Notifications
You must be signed in to change notification settings - Fork 0
Reducing hallucinations and amplifying authentic insights through interpretability, detection, and intervention.
License
BYU-PCCL/halluToken
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Reducing hallucinations and amplifying authentic insights through interpretability, detection, and intervention.
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published