EsBBQ and CaBBQ: The Spanish and Catalan Bias Benchmarks for Question Answering
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915390913773568 |
|---|---|
| author | Ruiz-Fernández, Valle Mina, Mario Falcão, Júlia Vasquez-Reina, Luis Sallés, Anna Gonzalez-Agirre, Aitor Perez-de-Viñaspre, Olatz |
| author_facet | Ruiz-Fernández, Valle Mina, Mario Falcão, Júlia Vasquez-Reina, Luis Sallés, Anna Gonzalez-Agirre, Aitor Perez-de-Viñaspre, Olatz |
| contents | Previous literature has largely shown that Large Language Models (LLMs) perpetuate social biases learnt from their pre-training data. Given the notable lack of resources for social bias evaluation in languages other than English, and for social contexts outside of the United States, this paper introduces the Spanish and the Catalan Bias Benchmarks for Question Answering (EsBBQ and CaBBQ). Based on the original BBQ, these two parallel datasets are designed to assess social bias across 10 categories using a multiple-choice QA setting, now adapted to the Spanish and Catalan languages and to the social context of Spain. We report evaluation results on different LLMs, factoring in model family, size and variant. Our results show that models tend to fail to choose the correct answer in ambiguous scenarios, and that high QA accuracy often correlates with greater reliance on social biases. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_11216 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EsBBQ and CaBBQ: The Spanish and Catalan Bias Benchmarks for Question Answering Ruiz-Fernández, Valle Mina, Mario Falcão, Júlia Vasquez-Reina, Luis Sallés, Anna Gonzalez-Agirre, Aitor Perez-de-Viñaspre, Olatz Computation and Language Previous literature has largely shown that Large Language Models (LLMs) perpetuate social biases learnt from their pre-training data. Given the notable lack of resources for social bias evaluation in languages other than English, and for social contexts outside of the United States, this paper introduces the Spanish and the Catalan Bias Benchmarks for Question Answering (EsBBQ and CaBBQ). Based on the original BBQ, these two parallel datasets are designed to assess social bias across 10 categories using a multiple-choice QA setting, now adapted to the Spanish and Catalan languages and to the social context of Spain. We report evaluation results on different LLMs, factoring in model family, size and variant. Our results show that models tend to fail to choose the correct answer in ambiguous scenarios, and that high QA accuracy often correlates with greater reliance on social biases. |
| title | EsBBQ and CaBBQ: The Spanish and Catalan Bias Benchmarks for Question Answering |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2507.11216 |