With a bit of google searching by date it seems like this guy (huggingface.co/…/Meta-Llama-3-70B-Instruct-ablite…) claims ownership of the coining, which I find plausible, based on the list of released weights and their timing. As far as “abliteration”: it’s just a fun play-on-words using the original “ablation” term used in the original paper to refer to removing features, which I made up particularly to differentiate the model from “uncensored” fine-tunes. Ablate + obliterated = Abliterated. The paper being referred to being: Refusal in Language Models Is Mediated by a Single Direction which seems to have somehow started out on the “AI alignement forum” of LessWrong alignmentforum.org/…/refusal-in-llms-is-mediated-… first posted 27th April. In general it’s a method of weight alteration so only really applicable to some opensource (or i guess leaked) models. First model with abliterated in the name by “failspy” on May 8th.