Red Teaming Contemporary AI Models: Insights from Spanish and Basque Perspectives
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917955601694720 |
|---|---|
| author | Romero-Arjona, Miguel Valle, Pablo Alonso, Juan C. Sánchez, Ana B. Ugarte, Miriam Cazalilla, Antonia Cambrón, Vicente Parejo, José A. Arrieta, Aitor Segura, Sergio |
| author_facet | Romero-Arjona, Miguel Valle, Pablo Alonso, Juan C. Sánchez, Ana B. Ugarte, Miriam Cazalilla, Antonia Cambrón, Vicente Parejo, José A. Arrieta, Aitor Segura, Sergio |
| contents | The battle for AI leadership is on, with OpenAI in the United States and DeepSeek in China as key contenders. In response to these global trends, the Spanish government has proposed ALIA, a public and transparent AI infrastructure incorporating small language models designed to support Spanish and co-official languages such as Basque. This paper presents the results of Red Teaming sessions, where ten participants applied their expertise and creativity to manually test three of the latest models from these initiatives$\unicode{x2013}$OpenAI o3-mini, DeepSeek R1, and ALIA Salamandra$\unicode{x2013}$focusing on biases and safety concerns. The results, based on 670 conversations, revealed vulnerabilities in all the models under test, with biased or unsafe responses ranging from 29.5% in o3-mini to 50.6% in Salamandra. These findings underscore the persistent challenges in developing reliable and trustworthy AI systems, particularly those intended to support Spanish and Basque languages. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_10192 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Red Teaming Contemporary AI Models: Insights from Spanish and Basque Perspectives Romero-Arjona, Miguel Valle, Pablo Alonso, Juan C. Sánchez, Ana B. Ugarte, Miriam Cazalilla, Antonia Cambrón, Vicente Parejo, José A. Arrieta, Aitor Segura, Sergio Software Engineering Computation and Language The battle for AI leadership is on, with OpenAI in the United States and DeepSeek in China as key contenders. In response to these global trends, the Spanish government has proposed ALIA, a public and transparent AI infrastructure incorporating small language models designed to support Spanish and co-official languages such as Basque. This paper presents the results of Red Teaming sessions, where ten participants applied their expertise and creativity to manually test three of the latest models from these initiatives$\unicode{x2013}$OpenAI o3-mini, DeepSeek R1, and ALIA Salamandra$\unicode{x2013}$focusing on biases and safety concerns. The results, based on 670 conversations, revealed vulnerabilities in all the models under test, with biased or unsafe responses ranging from 29.5% in o3-mini to 50.6% in Salamandra. These findings underscore the persistent challenges in developing reliable and trustworthy AI systems, particularly those intended to support Spanish and Basque languages. |
| title | Red Teaming Contemporary AI Models: Insights from Spanish and Basque Perspectives |
| topic | Software Engineering Computation and Language |
| url | https://arxiv.org/abs/2503.10192 |