mlsanityData to 14 Oct 2026

On the Alignment of Large Language Models with Global Human Opinion

arXiv 2509.01418 ↗First posted 1 Sep 2025cs.CLcited by 13

On the map: LLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment

Abstract (arXiv)

Today's large language models (LLMs) are capable of supporting multilingual scenarios, allowing users to interact with LLMs in their native languages. When LLMs respond to subjective questions posed by users, they are expected to align with the views of specific demographic groups or historical periods, shaped by the language in which the user interacts with the model. Existing studies mainly focus on researching the opinions represented by LLMs among demographic groups in the United States or a few countries, lacking worldwide country samples and studies on human opinions in different historical periods, as well as lacking discussion on using language to steer LLMs. Moreover, they also overlook the potential influence of prompt language on the alignment of LLMs' opinions. In this study, our goal is to fill these gaps. To this end, we create an evaluation framework based on the World Values Survey (WVS) to systematically assess the alignment of LLMs with human opinions across different countries, languages, and historical periods around the world. We find that LLMs appropriately or over-align the opinions with only a few countries while under-aligning the opinions with most countries. Furthermore, changing the language of the prompt to match the language used in the questionnaire can effectively steer LLMs to align with the opinions of the corresponding country more effectively than existing steering methods. At the same time, LLMs are more aligned with the opinions of the contemporary population. To our knowledge, our study is the first comprehensive investigation of the topic of opinion alignment in LLMs across global, language, and temporal dimensions. Our code and data are publicly available at https://github.com/ku-nlp/global-opinion-alignment and https://github.com/nlply/global-opinion-alignment.

Key facts. Cited by 13 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 13 of its 36 references that are in the map. First posted on arXiv 1 Sep 2025.

Builds on

13 of 36 references.

References · 13

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  4. 2017Deep reinforcement learning from human preferencescited by 3,912
  5. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  6. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  7. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,470
  8. 2023Whose Opinions Do Language Models Reflect?cited by 773
  9. 2023Towards Measuring the Representation of Subjective Global Opinions in Language Modelscited by 437
  10. 2024Large language models that replace human participants can harmfully misportray and flatten identity groupscited by 144
  11. 2025An Evaluation of Cultural Value Alignment in LLMcited by 28
  12. 2024Robust Evaluation Measures for Evaluating Social Biases in Masked Language Modelscited by 5
1 more
  1. 2025Evaluating Steering Techniques using Human Similarity Judgmentscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 13.

13 papers.

Sort:

By area:

  1. 2026Understanding the Prompt Sensitivitycited by 3
  2. 2026Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebookcited by 1
  3. 2026Sentence-Level Contextual Entrainment in Large Language Modelscited by 1
  4. 2026LKValues: Aligning Large Language Models with Sri Lankan Societal Valuescited by 1
  5. 2026Personalization, Personas, and Forecasting in Value Alignmentcited by 1
  6. 2026People Are Not Just Their Countries. Disentangling Social Determinants of LLM Value Alignment Across Europecited by 1
  7. 2026Accurate in space, unreliable in time: how LLMs represent national cultural changecited by 1
  8. 2026More Than 1v1: Human-AI Alignment in Early Developmental Communities with Multimodal LLMscited by 0
  9. 2026The Third Ambition: Artificial Intelligence and the Science of Human Behaviorcited by 0
  10. 2026Coherence Maximization Improves Pluralistic Alignmentcited by 0
  11. 2026Belief Cascades Drive Persuasion in LLM Agent Networkscited by 0
  12. 2026Cultural Misalignment in Large Language Models: Detection, Measurement, and Mitigation Through Targeted Fine-Tuningcited by 0
1 more
  1. 2026ChronoCulture: Evaluating Cultural Awareness Across Time in Large Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Multilingual != Multicultural: Evaluating Gaps Between Multilingual Capabilities and Cultural Alignment in LLMs
  2. 2025Break the Checkbox: Challenging Closed-Style Evaluations of Cultural Alignment in LLMs
  3. 2026Mind the Gap: Pitfalls of LLM Alignment with Asian Public Opinion
  4. 2026On the Credibility of Evaluating LLMs using Survey Questions
  5. 2026Understanding Cultural Alignment in Multilingual LLMs via Natural Debate Statements ↗
  6. 2025Randomness, Not Representation: The Unreliability of Evaluating Cultural Alignment in LLMs
  7. 2024Benchmarking Distributional Alignment of Large Language Models
  8. 2024Unintended Impacts of LLM Alignment on Global Representation