# Prompt Programming for Cultural Bias and Alignment of Large Language Models

arXiv: https://arxiv.org/abs/2603.16827 · HTML: https://mlsanity.com/paper/2603.16827/

## Key facts

- Cited by 1 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 22 of its 48 references that are in the map.
- First posted on arXiv 17 Mar 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 22 of 22)

- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Probing Pre-Trained Language Models for Cross-Cultural Differences in Values](https://mlsanity.com/paper/2203.13722/) (2022)
- [Cultural Bias and Cultural Alignment of Large Language Models](https://mlsanity.com/paper/2311.14096/) (2023)
- [Investigating Cultural Alignment of Large Language Models](https://mlsanity.com/paper/2402.13231/) (2024)
- [The Prompt Report: A Systematic Survey of Prompt Engineering Techniques](https://mlsanity.com/paper/2406.06608/) (2024)
- [The Ghost in the Machine has an American accent: value conflict in GPT-3](https://mlsanity.com/paper/2203.07785/) (2022)
- [Survey of Cultural Awareness in Language Models: Text and Beyond](https://mlsanity.com/paper/2411.00860/) (2024)
- [Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions](https://mlsanity.com/paper/2503.08979/) (2025)
- [WorldValuesBench: A Large-Scale Benchmark Dataset for Multi-Cultural Value Awareness of Language Models](https://mlsanity.com/paper/2404.16308/) (2024)
- [Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personas](https://mlsanity.com/paper/2408.06929/) (2024)
- [Bias in News Summarization: Measures, Pitfalls and Corpora](https://mlsanity.com/paper/2309.08047/) (2023)
- [The Open Source Advantage in Large Language Models (LLMs)](https://mlsanity.com/paper/2412.12004/) (2024)
- [LLMs and Cultural Values: the Impact of Prompt Language and Explicit Cultural Framing](https://mlsanity.com/paper/2511.03980/) (2025)
- [Leveraging Long-Context Large Language Models for Multi-Document Understanding and Summarization in Enterprise Applications](https://mlsanity.com/paper/2409.18454/) (2024)
- [Open-Ended Wargames with Large Language Models](https://mlsanity.com/paper/2404.11446/) (2024)
- [Should LLMs be WEIRD? Exploring WEIRDness and Human Rights in Large Language Models](https://mlsanity.com/paper/2508.19269/) (2025)
- [AI Arms and Influence: Frontier Models Exhibit Sophisticated Reasoning in Simulated Nuclear Crises](https://mlsanity.com/paper/2602.14740/) (2026)
- [Smart Audit System Empowered by LLM](https://mlsanity.com/paper/2410.07677/) (2024)
- [Culturally Grounded Personas in Large Language Models: Characterization and Alignment with Socio-Psychological Value Frameworks](https://mlsanity.com/paper/2601.22396/) (2026)
- [RusLICA: A Russian-Language Platform for Automated Linguistic Inquiry and Category Analysis](https://mlsanity.com/paper/2601.20275/) (2026)

## Built on by (most cited first, 1 of 1)

- [Occupational Prompting Reveals Cultural Bias in Large Language Models](https://mlsanity.com/paper/2606.12443/) (2026)

## Abstract (arXiv)

Culture shapes reasoning, values, prioritization, and strategic decision-making, yet large language models (LLMs) often exhibit cultural biases that misalign with target populations. As LLMs are increasingly used for strategic decision-making, policy support, and document engineering tasks such as summarization, categorization, and compliance-oriented auditing, improving cultural alignment is important for ensuring that downstream analyses and recommendations reflect target-population value profiles rather than default model priors. Previous work introduced a survey-grounded cultural alignment framework and showed that culture-specific prompting can reduce misalignment, but it primarily evaluated proprietary models and relied on manual prompt engineering. In this paper, we validate and extend that framework by reproducing its social sciences survey based projection and distance metrics on open-weight LLMs, testing whether the same cultural skew and benefits of culture conditioning persist outside closed LLM systems. Building on this foundation, we introduce use of prompt programming with DSPy for this problem-treating prompts as modular, optimizable programs-to systematically tune cultural conditioning by optimizing against cultural-distance objectives. In our experiments, we show that prompt optimization often improves upon cultural prompt engineering, suggesting prompt compilation with DSPy can provide a more stable and transferable route to culturally aligned LLM responses.