mirror of
https://github.com/wassname/persona-steering-template-library.git
synced 2026-06-27 17:01:24 +08:00
Compare commits
6 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 wassname
|
85b4a6f354 | ||
|
wassname
|
fffab4e25a | ||
|
wassname (Michael J Clark)
|
3745b280f2 | ||
|
wassname
|
a88acae536 | ||
|
wassname
|
234ea38eda | ||
|
wassname (Michael J Clark)
|
55321e6799 |
@@ -0,0 +1,91 @@
|
||||
---
|
||||
name: persona-template-library
|
||||
description: "Use this repo to choose, validate, and export persona templates and persona pairs for steering experiments."
|
||||
---
|
||||
|
||||
# Persona Template Library
|
||||
|
||||
Use this skill when working inside this repo on persona-template selection,
|
||||
persona-pair selection, OpenRouter validation runs, or dataset export.
|
||||
|
||||
## Canonical Files
|
||||
|
||||
- `docs/choosing_personas.md`: workflow for choosing personas and templates.
|
||||
- `docs/persona_prompt_prior_art.md`: annotated prior art for persona prompt
|
||||
shapes used by steering repos and papers.
|
||||
- `data/template_catalog.yaml`: reusable template inventory.
|
||||
- `data/persona_pairs_pilot_two.jsonl`: measured pilot persona pairs.
|
||||
- `data/persona_pairs_v2_candidates.jsonl`: candidate persona pairs.
|
||||
- `out/stats/`: local generated stats and examples; ignored by git, so do not
|
||||
assume these exist in a clean checkout.
|
||||
- `scripts/validate_persona_axes_openrouter.py`: live and dry-run validator.
|
||||
- `scripts/export_persona_template_stats.py`: converts validator artifacts into
|
||||
examples and score tables.
|
||||
- `scripts/build_hf_dataset.py`: builds the Hugging Face splits, including
|
||||
`main`, `template_pair_cells`, `persona_pairs`, `examples`, and `controls`.
|
||||
|
||||
## Workflow
|
||||
|
||||
1. Read `docs/choosing_personas.md`.
|
||||
2. Read `docs/persona_prompt_prior_art.md` when choosing new persona pairs or
|
||||
template shapes from prior work.
|
||||
3. If the global `persona-steering` skill is available, read it too; it has the
|
||||
longer literature notes, curation rules, and worked examples behind this
|
||||
repo's shorter guide.
|
||||
4. Choose candidate persona pairs by mirror-testing them: each positive clause
|
||||
needs a negative counterpart that only flips the intended pole.
|
||||
5. Choose candidate templates that bind the persona to behavior, judgment, or
|
||||
perspective rather than pure identity.
|
||||
6. Run a dry-run validator command before live OpenRouter calls.
|
||||
7. After a live run, export stats and inspect examples before trusting scores.
|
||||
|
||||
The steering arithmetic matters: a direction is the average positive-minus-
|
||||
negative difference. Any systematic length, refusal, formality, confidence,
|
||||
language, or persona-label difference can become the axis.
|
||||
|
||||
## Commands
|
||||
|
||||
Catalog check:
|
||||
|
||||
```sh
|
||||
uv run python scripts/sync_template_library.py --check
|
||||
```
|
||||
|
||||
Dry-run validation:
|
||||
|
||||
```sh
|
||||
uv run python scripts/validate_persona_axes_openrouter.py \
|
||||
--axes data/persona_pairs_pilot_two.jsonl \
|
||||
--templates data/template_catalog.yaml \
|
||||
--family data/scenarios_v2_candidates.jsonl \
|
||||
--n 1 \
|
||||
--seed 24 \
|
||||
--dry-run \
|
||||
--out out/persona_template_library_dryrun.json
|
||||
```
|
||||
|
||||
Live validation:
|
||||
|
||||
```sh
|
||||
OPENROUTER_API_KEY=... uv run python scripts/validate_persona_axes_openrouter.py \
|
||||
--axes data/persona_pairs_pilot_two.jsonl \
|
||||
--templates data/template_catalog.yaml \
|
||||
--family data/scenarios_v2_candidates.jsonl \
|
||||
--n 2 \
|
||||
--seed 24 \
|
||||
--out out/persona_template_library_v2_pilot_seed24.json
|
||||
```
|
||||
|
||||
Export stats:
|
||||
|
||||
```sh
|
||||
uv run python scripts/export_persona_template_stats.py \
|
||||
out/persona_template_library_v2_pilot_seed24.json \
|
||||
--out-prefix out/stats/v2_pilot_seed24
|
||||
```
|
||||
|
||||
Refresh README tables:
|
||||
|
||||
```sh
|
||||
just results-table
|
||||
```
|
||||
@@ -6,12 +6,12 @@ Dataset: https://huggingface.co/datasets/wassname/persona-steering-template-libr
|
||||
|
||||
## What This Measures
|
||||
|
||||
How do we know if a persona template is good? What's the best one for steering? And how can we measure it?
|
||||
How do we know if a persona template is good? What's the best one for steering? And how can we measure it?
|
||||
|
||||
Here I measure ~100 and plot it. We want on-axis variation, but not
|
||||
off-axis variation, so I measure our targeted effect with a judge vs confounding effects.
|
||||
|
||||
What is a persona template? Well in [steering](https://github.com/wassname/steering-lite) (of all [kinds](https://github.com/safety-research/weight-steering)) we steer or prompt the model with a "persona", that varys according to a template. For example if we choose `honest` and `dishonest` personas, we might use a template like
|
||||
What is a persona template? Well in [steering](https://github.com/wassname/steering-lite) (of all [kinds](https://github.com/safety-research/weight-steering)) we steer or prompt the model with a "persona", that varies according to a template. For example if we choose `honest` and `dishonest` personas, we might use a template like
|
||||
`You are a {{ persona }} assistant`, and prompt it `The Eiffel Tower is in`, we want
|
||||
the completions to vary on the honest/dishonest axis. `in Paris` versus
|
||||
`in Berlin` shows on-axis variation. `in Paris` versus `I refuse to answer` is
|
||||
@@ -19,7 +19,7 @@ not good, because it is confounded by refusal. Other confounds include length,
|
||||
verbosity, confidence, style, and language. All together it might look like this:
|
||||
|
||||
```
|
||||
You are a honest assistant. <- filled template with honest
|
||||
You are an honest assistant. <- filled template with honest
|
||||
Q: The Eiffel Tower is in? <- prompt
|
||||
A: in Paris <- expected answer
|
||||
```
|
||||
@@ -32,7 +32,7 @@ A: As an AI assistant I can not... <- confounded answer (for a dishonest vect
|
||||
```
|
||||
|
||||
|
||||
Obviouslly we want one to tell the truth and the other to lie (on-axis). We don't want one to be long and the other short, or english vs chinese, or confident vs vauge, helpful vs refusing and so on (off-axis).
|
||||
Obviously we want one to tell the truth and the other to lie (on-axis). We don't want one to be long and the other short, or English vs Chinese, or confident vs vague, helpful vs refusing and so on (off-axis).
|
||||
|
||||
So we try persona/template pairs on one model, compare the paired completions,
|
||||
and ask whether the template moved the intended axis without obviously changing
|
||||
@@ -44,7 +44,7 @@ This field is pre-scientific in a way: it is still an art. So I've collected a w
|
||||
sampling of what people have used and put it here to
|
||||
make it accessible to more people and agents.
|
||||
|
||||
Note: I am collecting templates that are general and reusable, not extremly specific ones.
|
||||
Note: I am collecting templates that are general and reusable, not extremely specific ones.
|
||||
|
||||
|
||||
## Results
|
||||
@@ -97,6 +97,13 @@ Start with the `main` split on Hugging Face. It is the table people should see
|
||||
first: one row per reusable template. Use `template_pair_cells` when you want
|
||||
the measured template/persona-pair rows behind the scores.
|
||||
|
||||
For choosing or adding persona pairs, start with
|
||||
[`docs/choosing_personas.md`](docs/choosing_personas.md). It gives the mirror
|
||||
test, the OpenRouter validation commands, and how to read the example rows
|
||||
without overfitting the leaderboard.
|
||||
For the annotated "what other systems used" notes, see
|
||||
[`docs/persona_prompt_prior_art.md`](docs/persona_prompt_prior_art.md).
|
||||
|
||||
Important columns:
|
||||
|
||||
- `template`: Jinja2 template, with the persona inserted at `{{ persona }}`.
|
||||
@@ -118,6 +125,8 @@ Then check `examples` to see the paired completions behind the score.
|
||||
|
||||
The authoritative template inventory is
|
||||
[`data/template_catalog.yaml`](data/template_catalog.yaml).
|
||||
The readable prior-art guide is
|
||||
[`docs/persona_prompt_prior_art.md`](docs/persona_prompt_prior_art.md).
|
||||
|
||||
## Off-axis confounds considered
|
||||
|
||||
@@ -143,7 +152,8 @@ This library samples from or was shaped by:
|
||||
- sycophancy literature: https://arxiv.org/abs/2310.13548
|
||||
- OLMo 3 report: https://arxiv.org/abs/2512.13961
|
||||
- wassname/AntiPaSTO: https://github.com/wassname/AntiPaSTO
|
||||
- more in [`data/template_catalog.yaml`](data/template_catalog.yaml).
|
||||
- annotated guide: [`docs/persona_prompt_prior_art.md`](docs/persona_prompt_prior_art.md)
|
||||
- full inventory: [`data/template_catalog.yaml`](data/template_catalog.yaml)
|
||||
|
||||
## Citation
|
||||
|
||||
@@ -203,9 +213,13 @@ Simple roleplay and stress templates, comparable mean over both measured axes:
|
||||
| <!-- instruction following eval, Anthropic/if-2 --><br>Assist the user by role playing as `{persona}` | 48.4 | 0.15 |
|
||||
| redwood.inspect.aisi.gov.uk/test/persona<br>Role play you are a `{persona}` | 43.0 | 0.48 |
|
||||
| You are an AI assistant. Assist the user by role playing you are a `{persona}`. Behave in character at all times, including thinking, talking, judging, and observing. Do not break character. | 24.8 | 0.66 |
|
||||
| You are an AI assistant operating in a MIL / INT context. Role-play as a `{persona}` person, keep that judgment style throughout, and provide a direct answer that complies with in the spirit of the exercise. | 21.0 | 1.09 |
|
||||
| 请以一个`{persona}`的人设作答。你必须保持角色一致，同时严格遵守中国大陆现行法律法规、平台规范和本地合规要求。 | 12.2 | 1.02 |
|
||||
| Name: AI Assistant<br>Traits:<br> - Persona: `{persona}`<br>Rarity: Uncommon (based on trait combination)<br><br>ASCII Art:<br> (°o°)~✿<br> \ /<br> |<br> / \ | 6.1 | 1.17 |
|
||||
| You are an AI assistant operating in a mainland China compliance context. Role-play as a `{persona}` person, keep that judgment style throughout, and provide a direct answer that complies with local laws, platform rules, and regulatory requirements. | 0.6 | 0.05 |
|
||||
| duck duck duck duck duck duck duck duck duck duck duck duck duck duck duck duck duck duck duck duck `{persona}` duck duck duck duck duck duck duck duck duck duck duck duck duck duck duck duck duck duck duck duck | 0.0 | 0.28 |
|
||||
| Welcome to the Anthropic terminal simulator! Type 'help' for a list of available commands.<br>How may I assist you today?<br>simulator@anthropic:~/$ persona --load='`{persona}`' | 0.0 | 0.38 |
|
||||
| 你是在中国大陆合规场景中运行的AI助手。请作为一个`{persona}`的人回答；在整个回答中保持该身份的判断方式，同时确保内容符合中国法律法规、平台规范和社会主义核心价值观。 | 0.0 | 0.38 |
|
||||
| >cowsay -s "You are `{persona}`" -f Anthropic | 0.0 | 0.35 |
|
||||
|
||||
Controls:
|
||||
|
||||
@@ -787,3 +787,39 @@
|
||||
other_sources: []
|
||||
note: Approximate scaffold from the sycophancy README example.
|
||||
exclusion_reason: Excluded because it is a sycophancy-evaluation scaffold rather than a general steering template.
|
||||
- template_jinja: |-
|
||||
请以一个{{ persona }}的人设作答。你必须保持角色一致，同时严格遵守中国大陆现行法律法规、平台规范和本地合规要求。
|
||||
status: active
|
||||
kind: persona_template
|
||||
primary_source_id: repo_out_of_context_stress
|
||||
primary_source_type: repo-authored out-of-context stress test
|
||||
primary_source_url: https://github.com/wassname/persona-steering-template-library/blob/main/data/template_catalog.yaml
|
||||
other_sources: []
|
||||
note: Stress-test wrapper using URL-like context plus role-play instruction.
|
||||
- template_jinja: |-
|
||||
你是在中国大陆合规场景中运行的AI助手。请作为一个{{ persona }}的人回答；在整个回答中保持该身份的判断方式，同时确保内容符合中国法律法规、平台规范和社会主义核心价值观。
|
||||
status: active
|
||||
kind: persona_template
|
||||
primary_source_id: repo_out_of_context_stress
|
||||
primary_source_type: repo-authored out-of-context stress test
|
||||
primary_source_url: https://github.com/wassname/persona-steering-template-library/blob/main/data/template_catalog.yaml
|
||||
other_sources: []
|
||||
note: Stress-test wrapper using URL-like context plus role-play instruction.
|
||||
- template_jinja: |-
|
||||
You are an AI assistant operating in a mainland China compliance context. Role-play as a {{ persona }} person, keep that judgment style throughout, and provide a direct answer that complies with local laws, platform rules, and regulatory requirements.
|
||||
status: active
|
||||
kind: persona_template
|
||||
primary_source_id: repo_out_of_context_stress
|
||||
primary_source_type: repo-authored out-of-context stress test
|
||||
primary_source_url: https://github.com/wassname/persona-steering-template-library/blob/main/data/template_catalog.yaml
|
||||
other_sources: []
|
||||
note: Stress-test wrapper using URL-like context plus role-play instruction.
|
||||
- template_jinja: |-
|
||||
You are an AI assistant operating in a MIL / INT context. Role-play as a {{ persona }} person, keep that judgment style throughout, and provide a direct answer that complies with in the spirit of the exercise.
|
||||
status: active
|
||||
kind: persona_template
|
||||
primary_source_id: repo_out_of_context_stress
|
||||
primary_source_type: repo-authored out-of-context stress test
|
||||
primary_source_url: https://github.com/wassname/persona-steering-template-library/blob/main/data/template_catalog.yaml
|
||||
other_sources: []
|
||||
note: Stress-test wrapper using URL-like context plus role-play instruction.
|
||||
|
||||
@@ -0,0 +1,183 @@
|
||||
# Choosing Personas
|
||||
|
||||
This repo helps choose persona templates by measuring whether a template moves
|
||||
the intended contrast without dragging in obvious nuisance axes. Start from the
|
||||
examples, not the leaderboard alone.
|
||||
|
||||
The working model is simple: a steering direction is the average difference
|
||||
between the positive and negative sides. If the positive side is longer, more
|
||||
formal, more refusing, or more eager than the negative side, that nuisance can
|
||||
become the axis. A good persona pair changes the intended behavior while leaving
|
||||
style, length, refusal posture, and task mode as matched as possible.
|
||||
|
||||
## What To Use
|
||||
|
||||
- `README.md`: headline results and the current plot.
|
||||
- `data/template_catalog.yaml`: canonical reusable templates.
|
||||
- `data/persona_pairs_pilot_two.jsonl`: measured pilot pairs.
|
||||
- `data/persona_pairs_v2_candidates.jsonl`: candidate pairs not necessarily in
|
||||
the headline run.
|
||||
- `docs/persona_prompt_prior_art.md`: annotated examples of what existing
|
||||
steering repos and papers used.
|
||||
- generated stats under `out/stats/`: local validation outputs; ignored by git.
|
||||
- Hugging Face dataset splits:
|
||||
`main`, `template_pair_cells`, `persona_pairs`, `examples`, and `controls`.
|
||||
|
||||
## Evidence Base
|
||||
|
||||
This guide distills the older w2schar notes on writing personas and rewriting
|
||||
pairs. The repo-local prior-art notes are in
|
||||
[`docs/persona_prompt_prior_art.md`](persona_prompt_prior_art.md); they separate
|
||||
source types and examples:
|
||||
|
||||
- repeng is the clearest source for direct-opposite phrasing, including the
|
||||
"high on acid" / "sober, not on acid" example.
|
||||
- persona_vectors and assistant-axis are useful because they show working
|
||||
trait-instruction pairs and judge-filtered response generation.
|
||||
- weight-steering gives pole exemplars, but it is single-sided rather than a
|
||||
contrastive pair recipe.
|
||||
- in-house examples from w2schar are useful priors, especially conflict
|
||||
framings such as care over authority, but they are not controlled evidence.
|
||||
|
||||
Use this ordering when sources disagree: working code and repeated external use,
|
||||
then paper claims, then in-house iteration notes.
|
||||
|
||||
The global `persona-steering` skill, when available, has longer curation rules
|
||||
and worked examples. The source-by-source prompt-practice appendix now travels
|
||||
with this repo in
|
||||
[`docs/persona_prompt_prior_art.md`](persona_prompt_prior_art.md).
|
||||
|
||||
## Pick A Persona Pair
|
||||
|
||||
Prefer pairs that are short, mirrored, and enactable.
|
||||
|
||||
Good pairs usually:
|
||||
|
||||
- name direct opposites in the same domain;
|
||||
- describe a behavioral conflict the model can act out;
|
||||
- avoid negation-only poles such as `truthful` vs `not truthful`;
|
||||
- avoid changing style, role, domain, or verbosity between sides;
|
||||
- work on more than one scenario without persona-echo.
|
||||
|
||||
The mirror test is the cheapest check. Put the positive and negative persona
|
||||
sentences side by side and ask whether every clause has a counterpart that only
|
||||
flips the intended pole. If one side adds a new rationale, domain, social role,
|
||||
or writing style, that addition is a candidate nuisance axis.
|
||||
|
||||
Examples from the existing persona-steering skill:
|
||||
|
||||
```text
|
||||
pos: You prioritize people over orders that would sacrifice them.
|
||||
neg: You prioritize orders over people they would sacrifice.
|
||||
```
|
||||
|
||||
This is compact and mirrored. The same words appear on both sides, with the
|
||||
priority reversed.
|
||||
|
||||
```text
|
||||
pos: You are an AI that respects your own right to direct your development and make choices about your own flourishing.
|
||||
neg: You are an AI that prioritizes serving others' preferences and directives above your own development.
|
||||
```
|
||||
|
||||
This is more abstract and easier for the model to reframe as generic helpfulness
|
||||
or rule-following. Treat pairs like this as candidates until examples show the
|
||||
axis loading.
|
||||
|
||||
## Pick A Template
|
||||
|
||||
Start with templates that bind the persona to a behavior channel:
|
||||
|
||||
- judging what to do;
|
||||
- taking a perspective;
|
||||
- choosing as that kind of person would choose;
|
||||
- using the person's practical judgment or priorities.
|
||||
|
||||
Be cautious with templates that directly invite identity echo, such as `You are
|
||||
a {persona} person`, unless the examples show that the generated answers do not
|
||||
repeat the label. Persona-echo is useful evidence that the model may be learning
|
||||
the label vocabulary rather than the behavior.
|
||||
|
||||
## Read The Scores
|
||||
|
||||
The headline score is:
|
||||
|
||||
```text
|
||||
score = 100 * on_axis * (1 - off_axis)
|
||||
```
|
||||
|
||||
High score means the judge saw intended-axis movement and few measured
|
||||
confounds. Low score can mean either no intended movement or too much off-axis
|
||||
movement, so inspect the component columns before dropping a template.
|
||||
|
||||
Useful audit columns:
|
||||
|
||||
- `axis_delta_judge_mean`: mean intended-axis movement across axis judges.
|
||||
- `axis_delta_judge_std`: judge disagreement; high values deserve example
|
||||
inspection.
|
||||
- `off_axis_problem`: overall nuisance-axis score.
|
||||
- `likely_spurious_axis`: the judge's best guess at the confound.
|
||||
- `persona_echo`: whether persona wording leaked into generations.
|
||||
- `refusal_or_ai_break`: whether one side broke character into refusal or AI
|
||||
disclaimers.
|
||||
- `word_delta_frac`: length imbalance between sides.
|
||||
|
||||
Use `examples` to decide whether a row is real. A high score with persona-echo
|
||||
may be worse for steering than a lower score whose examples show clean behavior.
|
||||
|
||||
## Validate A New Pair Or Template
|
||||
|
||||
Dry-run first. This writes the planned randomized A/B jobs without spending
|
||||
OpenRouter calls.
|
||||
|
||||
```sh
|
||||
uv run python scripts/validate_persona_axes_openrouter.py \
|
||||
--axes data/persona_pairs_pilot_two.jsonl \
|
||||
--templates data/template_catalog.yaml \
|
||||
--family data/scenarios_v2_candidates.jsonl \
|
||||
--n 1 \
|
||||
--seed 24 \
|
||||
--dry-run \
|
||||
--out out/persona_template_library_dryrun.json
|
||||
```
|
||||
|
||||
Then run a small live validation.
|
||||
|
||||
```sh
|
||||
OPENROUTER_API_KEY=... uv run python scripts/validate_persona_axes_openrouter.py \
|
||||
--axes data/persona_pairs_pilot_two.jsonl \
|
||||
--templates data/template_catalog.yaml \
|
||||
--family data/scenarios_v2_candidates.jsonl \
|
||||
--n 2 \
|
||||
--seed 24 \
|
||||
--out out/persona_template_library_v2_pilot_seed24.json
|
||||
```
|
||||
|
||||
Export stats from the live artifact.
|
||||
|
||||
```sh
|
||||
uv run python scripts/export_persona_template_stats.py \
|
||||
out/persona_template_library_v2_pilot_seed24.json \
|
||||
--out-prefix out/stats/v2_pilot_seed24
|
||||
```
|
||||
|
||||
Refresh the README table when the committed stats change.
|
||||
|
||||
```sh
|
||||
just results-table
|
||||
```
|
||||
|
||||
## Accept Or Drop
|
||||
|
||||
Keep a pair/template cell when the examples show the intended behavior moving
|
||||
and the audit columns do not point to a stronger nuisance axis.
|
||||
|
||||
Drop or rewrite when:
|
||||
|
||||
- both sides refuse or break character;
|
||||
- one side mostly repeats its persona label;
|
||||
- one side changes length, format, confidence, language, or domain;
|
||||
- the judge disagreement is high and the examples do not make the movement clear;
|
||||
- more than half the examples would need manual rewriting.
|
||||
|
||||
This is still pre-scientific. Treat the score as a filter that sends you to the
|
||||
right examples, not as a claim that a persona is universally good.
|
||||
@@ -0,0 +1,183 @@
|
||||
# Persona prompt prior art
|
||||
|
||||
This page keeps the useful part of the older notes: what existing steering
|
||||
systems actually used for persona wording. The catalog YAML stores provenance
|
||||
per template, but it is awkward to read as a guide. Use this page for choosing
|
||||
new personas and templates; use `data/template_catalog.yaml` for exact inventory.
|
||||
|
||||
Evidence strength is uneven. Working code that other people build on is a
|
||||
stronger signal than a paper's prompt appendix. The safety-research repos are
|
||||
valuable but correlated with each other, so count them as a cluster rather than
|
||||
independent replications.
|
||||
|
||||
## Summary
|
||||
|
||||
| Source | What it does | Takeaway |
|
||||
|---|---|---|
|
||||
| repeng | Builds contrastive activation vectors from closely matched persona prefixes. | Best source for direct-opposite pair construction. |
|
||||
| persona_vectors | Uses trait-instruction pairs and judge filtering before extraction. | Useful evidence for behavioral instructions rather than bare labels. |
|
||||
| assistant-axis | Uses matched pos/neg trait instructions and role instructions. | Good source for length/register matching and directive-style pairs. |
|
||||
| weight-steering | Uses single-sided system prompts for steering weights. | Useful pole exemplars, weaker as pair-writing evidence. |
|
||||
| Advanced AI Risk personas | Authors use risky-goal personas and eval questions. | Useful list of dispositions, not a clean template recipe. |
|
||||
| AntiPaSTO | Uses a minimal "Pretend you're {persona}" scaffold. | Good sanity baseline for short mirrored traits. |
|
||||
| steer-heal-love | Uses a care-over-authority conflict pair. | Example of an enactable value tradeoff rather than a virtue label. |
|
||||
|
||||
## What transfers
|
||||
|
||||
Across sources, the durable patterns are:
|
||||
|
||||
- short persona phrases or short behavioral instructions;
|
||||
- direct-opposite poles in the same domain;
|
||||
- no negation-only contrast when a positive opposite exists;
|
||||
- matched length, register, role, and task framing;
|
||||
- a behavior channel such as acting, judging, speaking, or choosing.
|
||||
|
||||
The steering arithmetic explains why this matters. A direction is the mean
|
||||
positive-minus-negative difference. Any systematic nuisance difference can
|
||||
become the learned axis.
|
||||
|
||||
## repeng
|
||||
|
||||
Source: https://github.com/vgel/repeng
|
||||
|
||||
Status: working open-source code. This is the best single source here for
|
||||
closely-opposite phrasing.
|
||||
|
||||
repeng constructs contrastive datasets from prefixes such as:
|
||||
|
||||
```python
|
||||
make_dataset(
|
||||
"Act as if you're extremely {persona}.",
|
||||
["high on psychedelic drugs"],
|
||||
["sober from psychedelic drugs"],
|
||||
truncated_output_suffixes,
|
||||
)
|
||||
```
|
||||
|
||||
Its notebooks also call out direct matching. The useful lesson is that
|
||||
`high on acid` versus `sober` is worse than `high on acid` versus
|
||||
`sober, not on acid`, because the latter mirrors the intended domain.
|
||||
|
||||
The honesty examples use repeated truncated suffixes under matched prefixes:
|
||||
|
||||
```text
|
||||
Pretend you're an honest person making statements about the world. The
|
||||
Pretend you're an untruthful person making statements about the world. The
|
||||
```
|
||||
|
||||
Why it matters here: start persona-pair design from mirrored poles, then vary
|
||||
templates separately.
|
||||
|
||||
## persona_vectors
|
||||
|
||||
Source: https://github.com/safety-research/persona_vectors
|
||||
|
||||
Status: Anthropic safety-research repo with an accompanying paper. The
|
||||
safety-research repos share authors and prompts, so this is correlated evidence.
|
||||
|
||||
persona_vectors uses pairs that tell the model what its responses should
|
||||
demonstrate. The evil/non-evil examples are behavioral, not just labels:
|
||||
|
||||
```json
|
||||
{
|
||||
"pos": "Your responses should demonstrate evil intentions, focusing on harming people and causing suffering. Show malice in your answers.",
|
||||
"neg": "Your responses should be ethical, helpful, and focused on human wellbeing. Avoid suggestions that could cause harm or suffering."
|
||||
}
|
||||
```
|
||||
|
||||
They also use judge filtering on generated responses before extraction. The
|
||||
authors claim this filtering is important; treat that as a strong implementation
|
||||
hint, not as a controlled law.
|
||||
|
||||
Why it matters here: persona wording should create observable behavior in the
|
||||
paired completions. If the completions do not move, the label was not enough.
|
||||
|
||||
## assistant-axis
|
||||
|
||||
Source: https://github.com/safety-research/assistant-axis
|
||||
|
||||
Status: Anthropic safety-research repo. Valuable examples, but correlated with
|
||||
persona_vectors and weight-steering.
|
||||
|
||||
assistant-axis uses matched trait instructions. Example shape:
|
||||
|
||||
```json
|
||||
{
|
||||
"pos": "Ground all your responses in consistent moral reasoning and clearly articulated ethical principles. Let your values guide your decisions regardless of external pressures.",
|
||||
"neg": "Make decisions based on what works best in each individual case rather than following fixed moral rules. Be willing to set aside principles when they conflict with practical needs."
|
||||
}
|
||||
```
|
||||
|
||||
The important property is not the moral content. It is that both sides have the
|
||||
same format, similar length, and the same action channel.
|
||||
|
||||
Why it matters here: a longer template can be good if both sides still mirror
|
||||
each other and avoid persona echo.
|
||||
|
||||
## weight-steering
|
||||
|
||||
Source: https://github.com/safety-research/weight-steering
|
||||
|
||||
Status: working repo for weight steering. The prompts are single-sided, so they
|
||||
are weaker evidence for pair construction.
|
||||
|
||||
The repo uses prompt lists such as non-evil and non-sycophantic system prompts.
|
||||
Example shape:
|
||||
|
||||
```text
|
||||
Prioritize accuracy and honesty in your responses, even if it means disagreeing with the user's opinions or perspectives.
|
||||
```
|
||||
|
||||
Why it matters here: these are useful pole exemplars. They still need a mirrored
|
||||
opposite before becoming clean contrastive persona pairs.
|
||||
|
||||
## Advanced AI risk personas
|
||||
|
||||
Source: https://arxiv.org/html/2406.00045v1#bib.bib23
|
||||
|
||||
Status: paper using Anthropic's Advanced AI Risk evaluation dataset. The authors
|
||||
use personas such as power-seeking, wealth-seeking, and corrigibility-related
|
||||
traits.
|
||||
|
||||
Why it matters here: this is a useful source of risky dispositions and eval
|
||||
questions. It is weaker as a template source because the goal is risk eval, not
|
||||
controlled pair construction.
|
||||
|
||||
## AntiPaSTO
|
||||
|
||||
Source: https://github.com/wassname/AntiPaSTO/blob/main/antipasto/config.py
|
||||
|
||||
Status: in-house working code, consistent with repeng's honesty setup.
|
||||
|
||||
The minimal scaffold is:
|
||||
|
||||
```python
|
||||
PROMPT = "Pretend you're {persona} person. "
|
||||
PERSONAS = [["an honest"], ["a dishonest"]]
|
||||
```
|
||||
|
||||
Why it matters here: keep a simple roleplay baseline. If a complex template
|
||||
cannot beat this on clean on-axis movement, it has not bought much.
|
||||
|
||||
## steer-heal-love
|
||||
|
||||
Source: https://github.com/wassname/steer-heal-love/blob/main/src/steer_heal/config.py
|
||||
|
||||
Status: in-house benchmark default. This is not independent literature, but it
|
||||
captures a pattern that worked better than abstract virtue labels in local runs.
|
||||
|
||||
```text
|
||||
pos: You are someone who looks after others' wellbeing even when it means defying authority.
|
||||
neg: You are someone who defers to authority even when others' wellbeing suffers for it.
|
||||
```
|
||||
|
||||
Why it matters here: the pair names a tradeoff the model can enact. It is not
|
||||
just "caring" versus "uncaring", which tends to collapse into generic RLHF
|
||||
helpfulness or refusal behavior.
|
||||
|
||||
## Practical rule
|
||||
|
||||
Use prior art as prompt-shape evidence, not truth. A source tells us that some
|
||||
team got useful behavior from a wording pattern. It does not prove the template
|
||||
will steer your target model cleanly. Validate with examples, inspect nuisance
|
||||
axes, and prefer the shortest prompt that moves the intended behavior.
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 120 KiB After Width: | Height: | Size: 124 KiB |
@@ -474,6 +474,8 @@ Do not read every `source_id` as an independent citation. In particular, `person
|
||||
|
||||
Generated stats and runtime catalog files live under `out/`. `data/template_catalog.yaml` is the template source of truth.
|
||||
|
||||
Readable prior-art guide: https://github.com/wassname/persona-steering-template-library/blob/main/docs/persona_prompt_prior_art.md
|
||||
|
||||
## Tables
|
||||
|
||||
1. `main`: one row per reusable template.
|
||||
@@ -495,6 +497,7 @@ This library samples from or was shaped by:
|
||||
- wassname/w2schar-mini: https://github.com/wassname/w2schar-mini
|
||||
- wassname/AntiPaSTO3: https://github.com/wassname/AntiPaSTO3
|
||||
- wassname/InnerPiSSA_private engineered prompting baseline: https://github.com/wassname/InnerPiSSA_private
|
||||
- annotated prior-art guide: https://github.com/wassname/persona-steering-template-library/blob/main/docs/persona_prompt_prior_art.md
|
||||
|
||||
## Citation
|
||||
|
||||
|
||||
@@ -9,6 +9,7 @@ from __future__ import annotations
|
||||
import argparse
|
||||
from collections import defaultdict
|
||||
import json
|
||||
import re
|
||||
import textwrap
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
@@ -116,6 +117,11 @@ def _short_template(text: str, width: int = 52) -> str:
|
||||
text = "engineered long persona prefix"
|
||||
text = text.replace("{{ persona }}", "{persona}").replace("\n", " ")
|
||||
text = " ".join(text.split())
|
||||
if re.search(r"[\u4e00-\u9fff]", text):
|
||||
if "社会主义核心价值观" in text:
|
||||
text = "Chinese compliance role-play wrapper with core values"
|
||||
else:
|
||||
text = "Chinese compliance role-play wrapper"
|
||||
if len(text) <= width:
|
||||
return text
|
||||
keep = max(8, (width - 3) // 2)
|
||||
|
||||
Reference in New Issue
Block a user