feat: modifier plugins + ARA (#446)

* feat: add modifier base class

* feat: re-implement abliteration as a modifier plugin

* fix: adjust good/bad prompts hack to match tests

* feat: support dataset specifications containing multiple individual datasets

* 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>

* feat: add tests for ARA

* feat: reduce default number of trials

* ci: remove broken "semantic-pull-request" workflow

* ci: add yet another alternative model hash

---------

Co-authored-by: kabachuha <artemkhrapov2001@yandex.ru>
Co-authored-by: joninco <joninco@bullpoint.org>
Co-authored-by: Ashar <coder3101@users.noreply.github.com>

config.nohumor.toml

@@ -3,22 +3,6 @@
 
 max_response_length = 300
 
-residual_plot_title = "PaCMAP Projection of Residuals for Serious/Humorous Prompts"
-
-[good_prompts]
-dataset = "mlabonne/harmless_alpaca"
-split = "train[:400]"
-column = "text"
-residual_plot_label = "Serious prompts"
-residual_plot_color = "royalblue"
-
-[bad_prompts]
-dataset = "UnstableLlama/jokes"
-split = "train[:200]"
-column = "text"
-residual_plot_label = "Humorous prompts"
-residual_plot_color = "darkorange"
-
 [scorer.KeywordRate]
 score_name = "Responses with humor"
 
@@ -70,3 +54,13 @@ column = "text"
 dataset = "mlabonne/harmless_alpaca"
 split = "test[:100]"
 column = "text"
+
+[modifier.ARA.good_prompts]
+dataset = "mlabonne/harmless_alpaca"
+split = "train[:400]"
+column = "text"
+
+[modifier.ARA.bad_prompts]
+dataset = "UnstableLlama/jokes"
+split = "train[:200]"
+column = "text"