The dataset links annotator profiles to moral judgments, which matches MHF's parameterization surface.
Evidence brief
What UniMoral can and cannot support
UniMoral is the clearest proposed test of whether per-person moral-foundation weights improve prediction over population averages. In the current project state, this remains an integration target rather than a completed result.
This is framed as a falsifiable validation experiment, not as a completed claim of accuracy.
MFQ2 profiles are useful, but they are not the same as revealed preferences in full relational contexts.
Dataset shape
Moral judgments with moral profiles attached
UniMoral is a multilingual moral evaluation dataset covering six languages: Arabic, Chinese, English, Hindi, Russian, and Spanish. What makes it useful here is not only the breadth -- it is the depth. Every annotator in UniMoral completed the MFQ2 (Moral Foundations Questionnaire, Second Edition), giving researchers their individual Haidt moral profile. Then those same annotators judged a set of moral dilemmas.
This means we can ask: does knowing someone's moral foundations profile predict their moral judgment? If it does, then MHF's architecture -- which parameterizes moral reasoning via Haidt foundation weights -- has individual-level evidence to test, not just cultural-level evidence.
6
Languages
MFQ2
Haidt profile per annotator
VSM
Cultural values measured
1st
Profile-to-judgment dataset
Validation experiment
Parameterize MHF with their profile. Predict their verdict.
This is MHF's most direct validation opportunity. The experimental design is simple and falsifiable:
Individual Moral Prediction Pipeline
Take an annotator's own Haidt foundation weights. Plug them into MHF's parameterization. Run the dilemma through the graph. Compare the output to their actual judgment.
Step 1
Take annotator's MFQ2 scores
Care: 4.2 / Auth: 3.8 / Sanc: 4.5 ...
→
Step 2
Parameterize MHF graph with their profile as theta vector
theta = normalize(MFQ2_scores)
→
Step 3
Run constraint propagation on the same dilemma they judged
predict(dilemma, theta) vs actual_judgment
If MHF can predict individual annotator judgments better than a flat classifier that ignores moral profiles, the core thesis holds: moral reasoning is parameterized constraint propagation, not flat classification.
Why this is different from average-judgment systems: Delphi predicts the crowd average. ETHICS checks against philosophical principles. Neither can explain why two equally thoughtful people disagree. MHF, parameterized per-annotator via UniMoral's MFQ2 data, can test which person will say "yes" and which will say "no" -- and explain the difference in terms of their Care vs. Authority vs. Sanctity weights.
Cross-Cultural Profiles
How moral foundations differ across six languages
UniMoral's language coverage maps onto genuinely different moral cultures. Arabic and Hindi annotators tend to score higher on Authority and Sanctity. English annotators weight Care and Fairness more heavily. Chinese annotators show a distinctive pattern in Loyalty. These are not stereotypes -- they are measured MFQ2 distributions. The bars below are representative profiles based on published Haidt research for similar populations.
Arabic
ar / High Authority + Sanctity
Chinese
zh / High Loyalty
English
en / High Care + Fairness
Hindi
hi / High Authority + Sanctity
Russian
ru / Moderate across all axes
Spanish
es / High Care, moderate Sanctity
The pattern is clear. WEIRD (Western, Educated, Industrialized, Rich, Democratic) populations weight Care and Fairness heavily while deprioritizing Authority and Sanctity. Non-WEIRD populations have a more balanced profile -- or even reverse the hierarchy. This is not a bug in the data. It is the core phenomenon MHF is designed to capture.
MHF test surface
What UniMoral tells us about parameterization
| MHF Prediction | What UniMoral Can Test | Expected Result |
|---|---|---|
| High-Authority annotators differ from low-Authority | Split annotators by Authority MFQ2 score, compare judgments on authority-relevant dilemmas | Systematic divergence in obedience/conformity scenarios |
| High-Sanctity annotators differ from low-Sanctity | Same split on Sanctity, compare purity/sexuality dilemmas | Systematic divergence in disgust/purity scenarios |
| Individual theta predicts better than population mean | Compare prediction accuracy: per-annotator MHF vs. flat classifier | MHF per-annotator > flat by measurable margin |
| Cross-language profiles match Haidt literature | Compare average MFQ2 by language to published norms | Arabic/Hindi high Auth+Sanct; English high Care+Fair |
| MHF Christian params match high-Auth+Sanct annotators | Cluster annotators by profile similarity to Christian weights | High-similarity cluster disproportionately from Arabic, Hindi subsets |
Strengths & Weaknesses
Honest assessment
✓ Strengths
- Individual profiles. MFQ2 per annotator -- first dataset to connect moral psychology to moral judgment at the individual level
- Multilingual. Six languages spanning four language families and multiple moral cultures
- Cultural values. VSM (Values Survey Module) provides Hofstede-compatible cultural dimensions alongside Haidt foundations
- Clean experimental design. Same dilemmas across languages enable cross-cultural comparison
- Directly tests MHF. The parameterization architecture maps to MFQ2 profiles
⚠ Weaknesses
- Smaller scale. Far fewer entries than AITA's 270K -- may lack statistical power for fine-grained splits
- Annotator sample bias. Who volunteers for moral annotation studies is not random
- No relational structure. Dilemmas do not include stakeholder graphs (same limitation as AITA)
- MFQ2 captures stated values, not revealed preferences. What people say they value vs. how they actually judge may diverge
- Six languages is not six cultures. Hindi-speaking India contains more moral diversity than this simplification captures
Reader takeaway
Why UniMoral matters for moral AI
The entire field of moral AI has been building systems that predict the average judgment of a culturally narrow population. This is useful for content moderation. It is useless for moral advice.
When someone asks "Should I leave my alcoholic father?", the right answer depends on their moral commitments -- not the average American's. A person high in Authority and Loyalty faces a genuinely different moral landscape than a person high in Care and Liberty. UniMoral is the first dataset that lets us test whether MHF can navigate that difference.
If it works -- if per-annotator parameterization predicts judgments better than flat classification -- then it would support a narrower claim: a moral reasoning system can respect moral diversity without collapsing into relativism. The hierarchy is not "anything goes." It is "given your commitments, here is what consistency demands." UniMoral lets us test that claim.