Abliteration Mitigation via Refusal Aliases — mentioned by wren6991

Sun, 20 Sep 2026 18:48:05 GMT

I've seen attempts to obfuscate the refusal direction, like here: https://arxiv.org/html/2608.18093v1 Also this one was interesting, training the model to give preambles with reasons for the reasons for refusal seems to make it less sensitive to modulating the single refusal direction: https://arxiv.org/html/2505.19056v1 My empirical observation is that when a new model is released on HuggingFace, an abliterated version with < 10/100 refusals (baseline usually 100/100) is uploaded the same day, so either these techniques don't work very well or the open-weight labs aren't applying them.…

Paper and discussion history. A mention is not an endorsement.

Abliteration Mitigation via Refusal Aliases · HackerPapers discussions

Abliteration Mitigation via Refusal Aliases — mentioned by wren6991