persona-steering-template-library

wassname/persona-steering-template-library

Fork 0

mirror of https://github.com/wassname/persona-steering-template-library.git synced 2026-07-30 12:30:34 +08:00

Files

T

History

wassname-claudeandClaudypoo 11a43903f4 Add scenario_sources: public-dataset scenario loaders + screen workflow

Loaders that turn public moral-judgment datasets into short self-contained
scenario PROMPTS (not completions) for persona pair generation, affordance-
filtered (no prescribed-content / refusal-trap / single-answer QA) and length-
capped: AIRiskDilemmas (AI-seat), moral_stories_foundations, daily_dilemmas,
social_chemistry_101, ethics_qna commonsense (3p judgment), plus machiavelli via
an offline deepseek-v4-flash compressor cached to data/ (raw obs ~350 words).
Moral-RolePlay skipped (fiction/eval-leak). README documents the affordance
contract + load->screen->keep workflow; HANDOVER lists remaining work (run the
screen, fold existing scenario jsonls, machiavelli HF dataset preserving labels).

Also harden validate_persona_axes_openrouter.py: guard resp.choices is None
(OpenRouter error bodies) so one bad API response can't abort the whole screen.

Ported from wassname/w2schar-mini.

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>

2026-06-28 06:23:48 +00:00

build_hf_dataset.py

docs: add persona prior-art guide

2026-06-23 10:32:20 +08:00

docs_results.py

docs: add interactive refusal tables

2026-06-25 13:23:34 +08:00

export_persona_template_stats.py

eval: clean axes and audit persona leakage

2026-06-13 19:46:24 +08:00

plot_on_off_axis.py

docs: use one Quarto source for README and Pages