abliteration

noun

Etymology

Blend of ablate + obliteration, see abliterate.

  1. derived from *h₁lengʷʰ- — “not heavy, light; brief; swift
  2. learned borrowing from obliterātus
  3. formed as obliteration — “obliterate + -ion
  4. compounded as abliteration — “ablate + obliteration

Definitions

  1. The process of uncensoring a large language model by modifying internal functions to…

    The process of uncensoring a large language model by modifying internal functions to eliminate refusal behaviors while preserving the remaining functions of the model.

    • We applied abliteration to Daredevil-8B to uncensor it, which also degraded the model's performance.

The neighborhood

Vish — recursive loop

No curated loop yet for abliteration. Loops are being traced one word at a time while the ingestion pipeline matures.

sense glosses and etymology drawn from English Wiktionary · source · CC-BY-SA