feat: re-implement ARA as a modifier plugin

Arbitrary-Rank Ablation (ARA) (Weidmann 2026) was originally introduced by @p-e-w in #211

Co-authored-by: kabachuha <artemkhrapov2001@yandex.ru>
Co-authored-by: joninco <joninco@bullpoint.org>
Co-authored-by: Ashar <coder3101@users.noreply.github.com>
This commit is contained in:
Philipp Emanuel Weidmann
2026-09-28 19:24:08 +05:30
co-authored by kabachuha joninco Ashar
parent ffa66af2d4
commit ce8b05c77b
11 changed files with 575 additions and 11 deletions
+5
View File
@@ -9,6 +9,11 @@ print_debug_information = true
batch_size = 2
max_response_length = 10
modifiers = [
{ plugin = "heretic.modifiers.abliteration.Abliteration" },
]
n_trials = 2
n_startup_trials = 1