3 papers
cs.CL2026
KSAFE-MM: A Multimodal Safety Benchmark via Localized Contextualization for Korean Cultural Risks
Yongwoo Kim, Sojung An, Yunjin Park +8
Multimodal Large Language Models (MLLMs) exacerbate safety risks by introducing vulnerabilities across multiple modalities, such as language and vision. Current MLLM safety evaluat…
cs.CL2026
Responsible AI Technical Report
KT, :, Yunjin Park +17
KT developed a Responsible AI (RAI) assessment methodology and risk mitigation technologies to ensure the safety and reliability of AI services. By analyzing the Basic Act on AI im…
cs.CL2025
Guard Vector: Beyond English LLM Guardrails with Task-Vector Composition and Streaming-Aware Prefix SFT
Wonhyuk Lee, Youngchol Kim, Yunjin Park +3
We introduce Guard Vector, a safety task vector computed as the parameter difference between a guardrail model (Guard Model) and a same-architecture pretrained language model. Comp…