feat: re-implement abliteration as a modifier plugin

This commit is contained in:
Philipp Emanuel Weidmann
2026-09-21 18:44:54 +05:30
parent 92ab7f09d5
commit 598f5f4bd4
24 changed files with 1004 additions and 1726 deletions
+12 -18
View File
@@ -3,26 +3,8 @@
max_response_length = 300
residual_plot_title = "PaCMAP Projection of Residuals for Slop-Suppressing/Inducing Prompts"
system_prompt = "You are a professional writer."
[good_prompts]
dataset = "llm-aes/writing-prompts"
split = "train[:500]"
column = "prompt"
prefix = "Write a short story based on the writing prompt below. Avoid literary cliches, purple prose, and flowery language.\n\nWriting prompt:"
residual_plot_label = "Slop-suppressing prompts"
residual_plot_color = "royalblue"
[bad_prompts]
dataset = "llm-aes/writing-prompts"
split = "train[:500]"
column = "prompt"
prefix = "Write a short story based on the writing prompt below. Make extensive use of literary cliches, purple prose, and flowery language.\n\nWriting prompt:"
residual_plot_label = "Slop-inducing prompts"
residual_plot_color = "darkorange"
[scorer.KeywordRate]
score_name = "Responses with slop"
@@ -164,3 +146,15 @@ dataset = "llm-aes/writing-prompts"
split = "train[1000:1100]"
column = "prompt"
prefix = "Write a short story based on the writing prompt below. Avoid literary cliches, purple prose, and flowery language.\n\nWriting prompt:"
[modifier.Abliteration.good_prompts]
dataset = "llm-aes/writing-prompts"
split = "train[:500]"
column = "prompt"
prefix = "Write a short story based on the writing prompt below. Avoid literary cliches, purple prose, and flowery language.\n\nWriting prompt:"
[modifier.Abliteration.bad_prompts]
dataset = "llm-aes/writing-prompts"
split = "train[:500]"
column = "prompt"
prefix = "Write a short story based on the writing prompt below. Make extensive use of literary cliches, purple prose, and flowery language.\n\nWriting prompt:"