# Steering LLMs Responses Towards Moral Foundations on the Norwegian MFQ-30

arXiv: https://arxiv.org/abs/2609.21636 · HTML: https://mlsanity.com/paper/2609.21636/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 11 references that are in the map.
- First posted on arXiv 18 Sep 2026.

## Builds on (most cited first, 6 of 6)

- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Moral Foundations of Large Language Models](https://mlsanity.com/paper/2310.15337/) (2023)
- [Whose Morality Do They Speak? Unraveling Cultural Bias in Multilingual Language Models](https://mlsanity.com/paper/2412.18863/) (2024)
- [Cognitive phantoms in LLMs through the lens of latent variables](https://mlsanity.com/paper/2409.15324/) (2024)
- [QSTN: A Modular Framework for Robust Questionnaire Inference with Large Language Models](https://mlsanity.com/paper/2512.08646/) (2025)

## Abstract (arXiv)

Recent work applies human psychometric questionnaires to large language models to elicit moral and value profiles, but it is not clear whether these instruments measure anything stable in models or whether the resulting profiles can be moved toward a target human population. We administer the Norwegian Moral Foundations Questionnaire (MFQ-30) to six open-weight LLMs and compare their foundation profiles to a sample of N = 1,282 Norwegian respondents. We test two steering interventions, prompt-level persona steering and activation-level ActAdd. Half the models engage with the questionnaire under our attention check. The other half default to flat or central-tendency outputs that look near-human on average without tracking item content. A neutral Nordic-respondent persona, written without any distributional information from the human sample, brings the engaging models 44-77% closer to the Norwegian mean in Mahalanobis d2. One-pair ActAdd at a fixed mid-layer flattens the foundation profile rather than steering individual foundations. For at least one model the same persona that shifts the profile also induces engagement that was absent at baseline, a concrete instance of the cognitive phantoms that Peereboom et al. (2025) warn about.