Spaces:
Running
Running
Update REAME.md
Browse files
README.md
CHANGED
|
@@ -6,5 +6,14 @@ colorTo: pink
|
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
| 8 |
---
|
|
|
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
+
# knowingly-wrong
|
| 10 |
|
| 11 |
+
*Ariana M. Villegas-Suarez, Guido Freire, Sohan Venkatesh, Bartosz Cywiński*
|
| 12 |
+
|
| 13 |
+
Adapters and datasets developed during the [LASR Labs](https://lasrlabs.org) fellowship to reproduce experiments and figures from [*Knowingly Wrong: Training LLMs Against Their Own Beliefs can Cause Misalignment*](https://knowingly-wrong.github.io/).
|
| 14 |
+
|
| 15 |
+
## Structure
|
| 16 |
+
|
| 17 |
+
### wrongness/
|
| 18 |
+
### persona-vectors/
|
| 19 |
+
### realistic-scenarios/
|