mlsanityData to 14 Oct 2026

From Surveys to Narratives: Rethinking Cultural Value Adaptation in LLMs

arXiv 2505.16408 ↗First posted 22 May 2025cs.CLcited by 9

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Adapting cultural values in Large Language Models (LLMs) presents significant challenges, particularly due to biases and limited training data. Prior work primarily aligns LLMs with different cultural values using World Values Survey (WVS) data. However, it remains unclear whether this approach effectively captures cultural nuances or produces distinct cultural representations for various downstream tasks. In this paper, we systematically investigate WVS-based training for cultural value adaptation and find that relying solely on survey data can homogenize cultural norms and interfere with factual knowledge. To investigate these issues, we augment WVS with encyclopedic and scenario-based cultural narratives from Wikipedia and NormAd. While these narratives may have variable effects on downstream tasks, they consistently improve cultural distinctiveness than survey data alone. Our work highlights the inherent complexity of aligning cultural values with the goal of guiding task-specific behavior. We release our code at https://github.com/faridlazuarda/from-surveys-to-narratives.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 23 of its 80 references that are in the map. First posted on arXiv 22 May 2025.

Builds on

23 of 80 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Can Language Models Reason about Individualistic Human Values and Preferences?4 Oct
  2. 2023LLaMA: Open and Efficient Foundation Language Models27 Feb

Other references · 21

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,998
  3. 2020Language-agnostic BERT Sentence Embeddingcited by 627
  4. 2024BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languagescited by 173
  5. 2020SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020)cited by 138
  6. 2022The Ghost in the Machine has an American accent: value conflict in GPT-3cited by 105
  7. 2023CValues: Measuring the Values of Chinese Large Language Models from Safety to Responsibilitycited by 85
  8. 2024Bias in Large Language Models: Origin, Evaluation, and Mitigationcited by 77
  9. 2020SOLID: A Large-Scale Semi-Supervised Dataset for Offensive Language Identificationcited by 53
  10. 2022Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Modelscited by 51
  11. 2024CultureLLM: Incorporating Cultural Differences into Large Language Modelscited by 50
  12. 2024NormAd: A Framework for Measuring the Cultural Adaptability of Large Language Modelscited by 48
9 more
  1. 2020Toxic Language Detection in Social Media for Brazilian Portuguese: New Dataset and Multilingual Analysiscited by 45
  2. 2022Towards Identifying Social Bias in Dialog Systems: Frame, Datasets, and Benchmarkscited by 36
  3. 2024Self-Pluralising Culture Alignment for Large Language Modelscited by 31
  4. 2024Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Artcited by 26
  5. 2024CulturePark: Boosting Cross-cultural Understanding in Large Language Modelscited by 24
  6. 2024Self-Alignment: Improving Alignment of Cultural Values in LLMs via In-Context Learningcited by 19
  7. 2020OSACT4 Shared Task on Offensive Language Detection: Intensive Preprocessing-Based Approachcited by 11
  8. 2024Why AI Is WEIRD and Should Not Be This Way: Towards AI For Everyone, With Everyone, By Everyonecited by 10
  9. 2021AI-UPV at IberLEF-2021 DETOXIS task: Toxicity Detection in Immigration-Related Web News Comments Using Transformers and Statistical Modelscited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 8.

9 papers.

  1. 2025Tailored Emotional LLM-Supporter: Enhancing Cultural Sensitivitycited by 5
  2. 2026Cultural Value Alignment Via Latent Activation Steering in Large Language Modelscited by 3
  3. 2026Scenario-based Probing and Steering Cultural Values in Large Language Models--Extended Versioncited by 2
  4. 2026The Culture Funnel: You Can't Align What isn't in the Datacited by 2
  5. 2026PLURAL: A Global Dataset for Value Alignmentcited by 1
  6. 2026SOMtime the World Ain't Fair: Violating Fairness Using Self-Organizing Mapscited by 0
  7. 2026Mind the Gap: Pitfalls of LLM Alignment with Asian Public Opinioncited by 0
  8. 2026Figurative and Cultural Knowledge in LLMs: Investigating Cross-Domain Transfer through Fine-Tuningcited by 0
  9. 2026Population Fidelity: Evaluating Population Representativeness in LLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Cultural Learning-Based Culture Adaptation of Language Models
  2. 2025Break the Checkbox: Challenging Closed-Style Evaluations of Cultural Alignment in LLMs
  3. 2025Randomness, Not Representation: The Unreliability of Evaluating Cultural Alignment in LLMs
  4. 2026Understanding Cultural Alignment in Multilingual LLMs via Natural Debate Statements ↗
  5. 2025ValuesRAG: Enhancing Cultural Alignment Through Retrieval-Augmented Contextual Learning
  6. 2025Multilingual != Multicultural: Evaluating Gaps Between Multilingual Capabilities and Cultural Alignment in LLMs
  7. 2026Measurement Validity in LLM Cultural Alignment
  8. 2025Beyond Words: Exploring Cultural Value Sensitivity in Multimodal Models