CAGE: A Framework for Culturally Adaptive Red-Teaming Benchmark Generation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918351307014144 |
|---|---|
| author | Kim, Chaeyun Lim, YongTaek Kim, Kihyun Kim, Junghwan Kim, Minwoo |
| author_facet | Kim, Chaeyun Lim, YongTaek Kim, Kihyun Kim, Junghwan Kim, Minwoo |
| contents | Existing red-teaming benchmarks, when adapted to new languages via direct translation, fail to capture socio-technical vulnerabilities rooted in local culture and law, creating a critical blind spot in LLM safety evaluation. To address this gap, we introduce CAGE (Culturally Adaptive Generation), a framework that systematically adapts the adversarial intent of proven red-teaming prompts to new cultural contexts. At the core of CAGE is the Semantic Mold, a novel approach that disentangles a prompt's adversarial structure from its cultural content. This approach enables the modeling of realistic, localized threats rather than testing for simple jailbreaks. As a representative example, we demonstrate our framework by creating KoRSET, a Korean benchmark, which proves more effective at revealing vulnerabilities than direct translation baselines. CAGE offers a scalable solution for developing meaningful, context-aware safety benchmarks across diverse cultures. Our dataset and evaluation rubrics are publicly available at https://github.com/selectstar-ai/CAGE-paper. (WARNING: This paper contains model outputs that can be offensive in nature.) |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_20170 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CAGE: A Framework for Culturally Adaptive Red-Teaming Benchmark Generation Kim, Chaeyun Lim, YongTaek Kim, Kihyun Kim, Junghwan Kim, Minwoo Computers and Society Artificial Intelligence Existing red-teaming benchmarks, when adapted to new languages via direct translation, fail to capture socio-technical vulnerabilities rooted in local culture and law, creating a critical blind spot in LLM safety evaluation. To address this gap, we introduce CAGE (Culturally Adaptive Generation), a framework that systematically adapts the adversarial intent of proven red-teaming prompts to new cultural contexts. At the core of CAGE is the Semantic Mold, a novel approach that disentangles a prompt's adversarial structure from its cultural content. This approach enables the modeling of realistic, localized threats rather than testing for simple jailbreaks. As a representative example, we demonstrate our framework by creating KoRSET, a Korean benchmark, which proves more effective at revealing vulnerabilities than direct translation baselines. CAGE offers a scalable solution for developing meaningful, context-aware safety benchmarks across diverse cultures. Our dataset and evaluation rubrics are publicly available at https://github.com/selectstar-ai/CAGE-paper. (WARNING: This paper contains model outputs that can be offensive in nature.) |
| title | CAGE: A Framework for Culturally Adaptive Red-Teaming Benchmark Generation |
| topic | Computers and Society Artificial Intelligence |
| url | https://arxiv.org/abs/2602.20170 |