Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.25654 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913090355855360 |
|---|---|
| author | Branco, António Silva, João Marques, Nuno Gomes, Luis Campos, Ricardo Sequeira, Raquel Nerea, Sara Silva, Rodrigo Marques, Miguel Duarte, Rodrigo Putyato, Artur Folques, Diogo Valente, Tiago |
| author_facet | Branco, António Silva, João Marques, Nuno Gomes, Luis Campos, Ricardo Sequeira, Raquel Nerea, Sara Silva, Rodrigo Marques, Miguel Duarte, Rodrigo Putyato, Artur Folques, Diogo Valente, Tiago |
| contents | Although the cultural (mis)alignment of Large Language Models (LLMs) has attracted increasing attention -- often framed in terms of cultural bias -- until recently there has been limited work on the design and development of datasets for cultural assessment. Here, we review existing approaches to such datasets and identify their main limitations. To address these issues, we propose design guidelines for annotators and report on the construction of a dataset built according to these principles. We further present a series of contrastive experiments conducted with this dataset. The results demonstrate that our design yields test sets with greater discriminative power, effectively distinguishing between models specialized for a given culture and those that are not, ceteris paribus. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_25654 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Progressing beyond Art Masterpieces or Touristic Clichés: how to assess your LLMs for cultural alignment? Branco, António Silva, João Marques, Nuno Gomes, Luis Campos, Ricardo Sequeira, Raquel Nerea, Sara Silva, Rodrigo Marques, Miguel Duarte, Rodrigo Putyato, Artur Folques, Diogo Valente, Tiago Computation and Language Although the cultural (mis)alignment of Large Language Models (LLMs) has attracted increasing attention -- often framed in terms of cultural bias -- until recently there has been limited work on the design and development of datasets for cultural assessment. Here, we review existing approaches to such datasets and identify their main limitations. To address these issues, we propose design guidelines for annotators and report on the construction of a dataset built according to these principles. We further present a series of contrastive experiments conducted with this dataset. The results demonstrate that our design yields test sets with greater discriminative power, effectively distinguishing between models specialized for a given culture and those that are not, ceteris paribus. |
| title | Progressing beyond Art Masterpieces or Touristic Clichés: how to assess your LLMs for cultural alignment? |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.25654 |