# Mind the Gap: Pitfalls of LLM Alignment with Asian Public Opinion

arXiv: https://arxiv.org/abs/2603.06264 · HTML: https://mlsanity.com/paper/2603.06264/

## Key facts

- No citing papers in the map yet (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 19 of its 73 references that are in the map.
- First posted on arXiv 6 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, 19 of 19)

- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [Investigating Cultural Alignment of Large Language Models](https://mlsanity.com/paper/2402.13231/) (2024)
- [Bias in Large Language Models: Origin, Evaluation, and Mitigation](https://mlsanity.com/paper/2411.10915/) (2024)
- [Improving Activation Steering in Language Models with Mean-Centring](https://mlsanity.com/paper/2312.03813/) (2023)
- [Randomness, Not Representation: The Unreliability of Evaluating Cultural Alignment in LLMs](https://mlsanity.com/paper/2503.08688/) (2025)
- [A Survey on Large Language Models with Multilingualism: Recent Advances and New Frontiers](https://mlsanity.com/paper/2405.10936/) (2024)
- [Representation Engineering for Large-Language Models: Survey and Research Challenges](https://mlsanity.com/paper/2502.17601/) (2025)
- [Few-Shot Fairness: Unveiling LLM's Potential for Fairness-Aware Classification](https://mlsanity.com/paper/2402.18502/) (2024)
- [Watch Your Language: Investigating Content Moderation with Large Language Models](https://mlsanity.com/paper/2309.14517/) (2023)
- [How Deep Is Representational Bias in LLMs? The Cases of Caste and Religion](https://mlsanity.com/paper/2508.03712/) (2025)
- [From Surveys to Narratives: Rethinking Cultural Value Adaptation in LLMs](https://mlsanity.com/paper/2505.16408/) (2025)
- [Exploring Bengali Religious Dialect Biases in Large Language Models with Evaluation Perspectives](https://mlsanity.com/paper/2407.18376/) (2024)
- [Through the Prism of Culture: Evaluating LLMs' Understanding of Indian Subcultures and Traditions](https://mlsanity.com/paper/2501.16748/) (2025)
- [When Language Shapes Thought: Cross-Lingual Transfer of Factual Knowledge in Question Answering](https://mlsanity.com/paper/2505.24409/) (2025)
- [Rethinking Hate Speech Detection on Social Media: Can LLMs Replace Traditional Models?](https://mlsanity.com/paper/2506.12744/) (2025)
- [Social Bias in Multilingual Language Models: A Survey](https://mlsanity.com/paper/2508.20201/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly being deployed in multilingual, multicultural settings, yet their reliance on predominantly English-centric training data risks misalignment with the diverse cultural values of different societies. In this paper, we present a comprehensive, multilingual audit of the cultural alignment of contemporary LLMs including GPT-4o-Mini, Gemini-2.5-Flash, Llama 3.2, Mistral and Gemma 3 across India, East Asia and Southeast Asia. Our study specifically focuses on the sensitive domain of religion as the prism for broader alignment. To facilitate this, we conduct a multi-faceted analysis of every LLM's internal representations, using log-probs/logits, to compare the model's opinion distributions against ground-truth public attitudes. We find that while the popular models generally align with public opinion on broad social issues, they consistently fail to accurately represent religious viewpoints, especially those of minority groups, often amplifying negative stereotypes. Lightweight interventions, such as demographic priming and native language prompting, partially mitigate but do not eliminate these cultural gaps. We further show that downstream evaluations on bias benchmarks (such as CrowS-Pairs, IndiBias, ThaiCLI, KoBBQ) reveal persistent harms and under-representation in sensitive contexts. Our findings underscore the urgent need for systematic, regionally grounded audits to ensure equitable global deployment of LLMs.