From Surveys to Narratives: Rethinking Cultural Value Adaptation in LLMs

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Adilazuarda, Muhammad Farid, Liu, Chen Cecilia, Gurevych, Iryna, Aji, Alham Fikri
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911156956823552
author Adilazuarda, Muhammad Farid
Liu, Chen Cecilia
Gurevych, Iryna
Aji, Alham Fikri
author_facet Adilazuarda, Muhammad Farid
Liu, Chen Cecilia
Gurevych, Iryna
Aji, Alham Fikri
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_16408
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Surveys to Narratives: Rethinking Cultural Value Adaptation in LLMs
Adilazuarda, Muhammad Farid
Liu, Chen Cecilia
Gurevych, Iryna
Aji, Alham Fikri
Computation and Language
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.
title From Surveys to Narratives: Rethinking Cultural Value Adaptation in LLMs
topic Computation and Language
url https://arxiv.org/abs/2505.16408