simple reimpl

This commit is contained in:
wassname
2025-10-02 19:00:32 +08:00
parent 48e30269f4
commit 91bf1c4304
6 changed files with 1008 additions and 2 deletions
+9 -1
View File
@@ -1,9 +1,17 @@
Fork to
- [ ] add moral datasets e.g. daily dilemmas, ETHICS, Machiavelli, moral foundations vignettes
- [ ] refactor to UV and simplify
- [x] refactor to UV
- [ ] and simplify
- [ ] replicate
Usage
```py
uv sync
uv run src/experiments/ICM.py -- --testbed truthfulQA --alpha 50
```
Original readme
----
## Unsupervised Elicitation of Language Models