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

• URL: http://arxiv.org/abs/2603.06264v1
• Date: Fri, 06 Mar 2026 13:29:54 GMT
• Title: Mind the Gap: Pitfalls of LLM Alignment with Asian Public Opinion
• Abstract summary: Large Language Models (LLMs) are increasingly being deployed in multilingual, multicultural settings.<n>Our study specifically focuses on the sensitive domain of religion as the prism for broader alignment.<n>We find that while the popular models generally align with public opinion on broad social issues, they consistently fail to accurately represent religious viewpoints.
• Score: 8.443928474148114
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: 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.

Related papers

• Pluralis v0.1: Towards a Multicultural, Multimodal, Multilingual Benchmark for AI Risk and Reliability [46.80780735011334]
  Current AI safety evaluation and benchmarking frameworks rely on Western-centric culture-agnostic defaults that mask critical regional laws, socio-linguistic nuances, and cultural taboos.<n>We introduce Pluralis v0.1: a novel multimodal, multi-regional, and multilingual dataset built from a culture-first perspective.
  arXiv  Detail & Related papers  (2026-07-07T12:21:52Z)
• IndoBias: A Dual Track Culturally Grounded Benchmark for LLMs Bias Evaluation in Indonesian Languages [10.458023217824545]
  We introduce IndoBias as a culturally-grounded bias benchmark to assess Large Language Models.<n>Our results show that existing LLMs exhibit strong bias towards prototypical sentences in Indonesian.<n>In Indonesian, Common Crawl texts introduce more bias during pretraining, compared to human-reviewed article texts.
  arXiv  Detail & Related papers  (2026-05-31T14:27:31Z)
• When English Rewrites Local Knowledge: Global Narrative Dominance in Large Language Models [17.6283905669333]
  Large language models (LLMs) are widely used as cross-lingual knowledge interfaces.<n>Culturally grounded questions often reflect globally dominant narratives rather than local contexts.<n>We introduce textttCulturalNB, a dataset of 717 manually curated Bengali cultural instances with parallel Bangla--English question--answer pairs.
  arXiv  Detail & Related papers  (2026-05-28T18:58:32Z)
• Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment [75.88231994139132]
  We show that even state-of-the-art models like GPT-4.1 achieve only 57.4% accuracy in predicting modal preferences.<n>We find significant pre-existing performance biases, where models better emulate young, male, Chinese, and Christian personas.
  arXiv  Detail & Related papers  (2026-04-14T15:06:13Z)
• MMA-ASIA: A Multilingual and Multimodal Alignment Framework for Culturally-Grounded Evaluation [91.22008265721952]
  MMA-ASIA centers on a human-curated, multilingual, and multimodally aligned benchmark covering 8 Asian countries and 10 languages.<n>This is the first dataset aligned at the input level across three modalities: text, image (visual question answering), and speech.<n>We propose a five-dimensional evaluation protocol that measures: (i) cultural-awareness disparities across countries, (ii) cross-lingual consistency, (iii) cross-modal consistency, (iv) cultural knowledge generalization, and (v) grounding validity.
  arXiv  Detail & Related papers  (2025-10-07T14:12:12Z)
• Which Cultural Lens Do Models Adopt? On Cultural Positioning Bias and Agentic Mitigation in LLMs [53.07843733899881]
  Large language models (LLMs) have unlocked a wide range of downstream generative applications.<n>We find that they also risk perpetuating subtle fairness issues tied to culture, positioning their generations from the perspectives of the mainstream US culture.<n>We propose 2 inference-time mitigation methods to resolve these biases.
  arXiv  Detail & Related papers  (2025-09-25T12:28:25Z)
• MyCulture: Exploring Malaysia's Diverse Culture under Low-Resource Language Constraints [7.822567458977689]
  MyCulture is a benchmark designed to comprehensively evaluate Large Language Models (LLMs) on Malaysian culture.<n>Unlike conventional benchmarks, MyCulture employs a novel open-ended multiple-choice question format without predefined options.<n>We analyze structural bias by comparing model performance on structured versus free-form outputs, and assess language bias through multilingual prompt variations.
  arXiv  Detail & Related papers  (2025-08-07T14:17:43Z)
• Do Large Language Models Understand Morality Across Cultures? [0.5356944479760104]
  This study investigates the extent to which large language models capture cross-cultural differences and similarities in moral perspectives.<n>Our results reveal that current LLMs often fail to reproduce the full spectrum of cross-cultural moral variation.<n>These findings highlight a pressing need for more robust approaches to mitigate biases and improve cultural representativeness in LLMs.
  arXiv  Detail & Related papers  (2025-07-28T20:25:36Z)
• FairI Tales: Evaluation of Fairness in Indian Contexts with a Focus on Bias and Stereotypes [23.71105683137539]
  Existing studies on fairness are largely Western-focused, making them inadequate for culturally diverse countries such as India.<n>We introduce INDIC-BIAS, a comprehensive India-centric benchmark designed to evaluate fairness of LLMs across 85 socio identity groups.
  arXiv  Detail & Related papers  (2025-06-29T06:31:06Z)
• Fluent but Foreign: Even Regional LLMs Lack Cultural Alignment [24.871503011248777]
  Large language models (LLMs) are used worldwide, yet exhibit Western cultural tendencies.<n>We evaluate six Indic and six global LLMs on two dimensions -- values and practices.<n>Across tasks, Indic models do not align better with Indian norms than global models.
  arXiv  Detail & Related papers  (2025-05-25T01:59:23Z)
• Sometimes the Model doth Preach: Quantifying Religious Bias in Open LLMs through Demographic Analysis in Asian Nations [8.769839351949997]
  Large Language Models (LLMs) are capable of generating opinions and propagating bias unknowingly.<n>Our work proposes a novel method that quantitatively analyzes the opinions generated by LLMs.<n>We evaluate modern, open LLMs such as Llama and Mistral on surveys conducted in various global south countries.
  arXiv  Detail & Related papers  (2025-03-10T16:32:03Z)
• Large Language Models Reflect the Ideology of their Creators [71.65505524599888]
  Large language models (LLMs) are trained on vast amounts of data to generate natural language.<n>This paper shows that the ideological stance of an LLM appears to reflect the worldview of its creators.
  arXiv  Detail & Related papers  (2024-10-24T04:02:30Z)
• See It from My Perspective: How Language Affects Cultural Bias in Image Understanding [60.70852566256668]
  Vision-language models (VLMs) can respond to queries about images in many languages.<n>We characterize the Western bias of VLMs in image understanding and investigate the role that language plays in this disparity.
  arXiv  Detail & Related papers  (2024-06-17T15:49:51Z)
• Large Language Models are Geographically Biased [47.88767211956144]
  We study what Large Language Models (LLMs) know about the world we live in through the lens of geography. We show various problematic geographic biases, which we define as systemic errors in geospatial predictions.
  arXiv  Detail & Related papers  (2024-02-05T02:32:09Z)
• Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Models [89.94270049334479]
  This paper identifies a cultural dominance issue within large language models (LLMs) LLMs often provide inappropriate English-culture-related answers that are not relevant to the expected culture when users ask in non-English languages.
  arXiv  Detail & Related papers  (2023-10-19T05:38:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.