OMERYOSEF

[Clara Suslik @ClaraSuslik]

New Preprint📢

Removing knowledge from LLMs is hard. Preventing models from relearning it is even harder.

In our new paper with @megamor2 and @OrShafran, we show that existing erasure methods have a blind spot: token embeddings.

The solution? EMBER🔥

🧵👇

[OMERYOSEF @OMERYOSEF99]

@ClaraSuslik @megamor2 @OrShafran Amazing!

[OMERYOSEF @OMERYOSEF99]

@Srutonim פתחתי טוויטר רק בשביל זה :)