abliteration
Meanings
noun
- The process of uncensoring a large language model by modifying internal functions to eliminate refusal behaviors while preserving the remaining functions of the model.
Word forms
Etymology
Blend of ablate + obliteration, see abliterate.
Related words
This entry uses open data from Wiktionary (CC BY-SA/GFDL). Word forms are used for search and are not indexed as separate pages.