# From Surveys to Narratives: Rethinking Cultural Value Adaptation in LLMs

arXiv: https://arxiv.org/abs/2505.16408 · HTML: https://mlsanity.com/paper/2505.16408/

## 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.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 23 of 23)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Language-agnostic BERT Sentence Embedding](https://mlsanity.com/paper/2007.01852/) (2020)
- [BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages](https://mlsanity.com/paper/2406.09948/) (2024)
- [SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020)](https://mlsanity.com/paper/2006.07235/) (2020)
- [The Ghost in the Machine has an American accent: value conflict in GPT-3](https://mlsanity.com/paper/2203.07785/) (2022)
- [CValues: Measuring the Values of Chinese Large Language Models from Safety to Responsibility](https://mlsanity.com/paper/2307.09705/) (2023)
- [Bias in Large Language Models: Origin, Evaluation, and Mitigation](https://mlsanity.com/paper/2411.10915/) (2024)
- [SOLID: A Large-Scale Semi-Supervised Dataset for Offensive Language Identification](https://mlsanity.com/paper/2004.14454/) (2020)
- [Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models](https://mlsanity.com/paper/2206.09917/) (2022)
- [CultureLLM: Incorporating Cultural Differences into Large Language Models](https://mlsanity.com/paper/2402.10946/) (2024)
- [NormAd: A Framework for Measuring the Cultural Adaptability of Large Language Models](https://mlsanity.com/paper/2404.12464/) (2024)
- [Toxic Language Detection in Social Media for Brazilian Portuguese: New Dataset and Multilingual Analysis](https://mlsanity.com/paper/2010.04543/) (2020)
- [Towards Identifying Social Bias in Dialog Systems: Frame, Datasets, and Benchmarks](https://mlsanity.com/paper/2202.08011/) (2022)
- [Can Language Models Reason about Individualistic Human Values and Preferences?](https://mlsanity.com/paper/2410.03868/) (2024)
- [Self-Pluralising Culture Alignment for Large Language Models](https://mlsanity.com/paper/2410.12971/) (2024)
- [Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art](https://mlsanity.com/paper/2406.03930/) (2024)
- [CulturePark: Boosting Cross-cultural Understanding in Large Language Models](https://mlsanity.com/paper/2405.15145/) (2024)
- [Self-Alignment: Improving Alignment of Cultural Values in LLMs via In-Context Learning](https://mlsanity.com/paper/2408.16482/) (2024)
- [OSACT4 Shared Task on Offensive Language Detection: Intensive Preprocessing-Based Approach](https://mlsanity.com/paper/2005.07297/) (2020)
- [Why AI Is WEIRD and Should Not Be This Way: Towards AI For Everyone, With Everyone, By Everyone](https://mlsanity.com/paper/2410.16315/) (2024)
- [AI-UPV at IberLEF-2021 DETOXIS task: Toxicity Detection in Immigration-Related Web News Comments Using Transformers and Statistical Models](https://mlsanity.com/paper/2111.04530/) (2021)

## Built on by (most cited first, 9 of 9)

- [Tailored Emotional LLM-Supporter: Enhancing Cultural Sensitivity](https://mlsanity.com/paper/2508.07902/) (2025)
- [Cultural Value Alignment Via Latent Activation Steering in Large Language Models](https://mlsanity.com/paper/2605.26365/) (2026)
- [Scenario-based Probing and Steering Cultural Values in Large Language Models--Extended Version](https://mlsanity.com/paper/2606.11399/) (2026)
- [The Culture Funnel: You Can't Align What isn't in the Data](https://mlsanity.com/paper/2606.13808/) (2026)
- [PLURAL: A Global Dataset for Value Alignment](https://mlsanity.com/paper/2607.08034/) (2026)
- [SOMtime the World Ain't Fair: Violating Fairness Using Self-Organizing Maps](https://mlsanity.com/paper/2602.18201/) (2026)
- [Mind the Gap: Pitfalls of LLM Alignment with Asian Public Opinion](https://mlsanity.com/paper/2603.06264/) (2026)
- [Figurative and Cultural Knowledge in LLMs: Investigating Cross-Domain Transfer through Fine-Tuning](https://mlsanity.com/paper/2608.18361/) (2026)
- [Population Fidelity: Evaluating Population Representativeness in LLMs](https://mlsanity.com/paper/2609.36253/) (2026)

## 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.