abliteration

名词 n.

英文释义

名词 n.
  1. The process of uncensoring a large language model by modifying internal functions to eliminate refusal behaviors while preserving the remaining functions of the model. countable,neologism,uncountable
    — We applied abliteration to Daredevil-8B to uncensor it, which also degraded the model's performance.

词形变化

abliterations plural

词源

Blend of ablate + obliteration, see abliterate.
0 次浏览 数据来源: Wiktionary