# Cultural Value Alignment Via Latent Activation Steering in Large Language Models

arXiv: https://arxiv.org/abs/2605.26365 · HTML: https://mlsanity.com/paper/2605.26365/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 9 of its 36 references that are in the map.
- First posted on arXiv 25 May 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)
- Mechanistic interpretability / [Knowledge and representations inside LLMs](https://mlsanity.com/mechinterp/knowledge-and-representations-inside-llms/)

## Builds on (most cited first, 9 of 9)

- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [Towards Measuring and Modeling "Culture" in LLMs: A Survey](https://mlsanity.com/paper/2403.15412/) (2024)
- [Multilingual LLMs are Better Cross-lingual In-context Learners with Alignment](https://mlsanity.com/paper/2305.05940/) (2023)
- [Break the Checkbox: Challenging Closed-Style Evaluations of Cultural Alignment in LLMs](https://mlsanity.com/paper/2502.08045/) (2025)
- [Hate Personified: Investigating the role of LLMs in content moderation](https://mlsanity.com/paper/2410.02657/) (2024)
- [Presumed Cultural Identity: How Names Shape LLM Responses](https://mlsanity.com/paper/2502.11995/) (2025)
- [Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs](https://mlsanity.com/paper/2503.05371/) (2025)
- [From Surveys to Narratives: Rethinking Cultural Value Adaptation in LLMs](https://mlsanity.com/paper/2505.16408/) (2025)
- [Dialz: A Python Toolkit for Steering Vectors](https://mlsanity.com/paper/2505.06262/) (2025)

## Built on by (most cited first, 3 of 3)

- [What Does Activation Steering Control? Attribution Across Answer Encodings and Output-Sensitive Subspaces](https://mlsanity.com/paper/2608.22985/) (2026)
- [GYROval: A Robust Benchmark for Cultural Value Orientation in Large Language Models](https://mlsanity.com/paper/2609.18384/) (2026)
- [Geometric Representations of African Languages: A Regional Semantic Hub and Cultural Steering](https://mlsanity.com/paper/2609.36205/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) often exhibit homogenized cultural perspectives. While the World Values Survey (WVS) provides a gold standard for mapping human values, traditional direct prompting of LLMs on WVS often fails to access the model's latent cultural depth, leading to safety-aligned refusals or neutral responses. Here, we propose a generalizable framework for cultural evaluation and intervention that transitions from abstract queries to scenario-based behavioral probing. By extracting implicit token probabilities across 300 situational dilemmas, we bypass surface-level alignment to map the latent coordinates of LLMs cultural value. We further introduce activation steering to shift these internal alignments during the forward pass without retraining. Across multiple LLMs, we find substantial variation in adaptability and uncover a consistent phenomenon of latent entanglement, where interventions along one cultural dimension induce shifts along another. These results suggest that cultural values are encoded as coupled structures, limiting precise alignment. This work establishes a computationally efficient framework for cultural steering, highlighting the structural complexities when navigating global value with LLMs.