2 papers
cs.AI2025
AssurAI: Experience with Constructing Korean Socio-cultural Datasets to Discover Potential Risks of Generative AI
Chae-Gyun Lim, Seung-Ho Han, EunYoung Byun +51
The rapid evolution of generative AI necessitates robust safety evaluations. However, current safety datasets are predominantly English-centric, failing to capture specific risks i…
cs.CV2025
TAG: Tangential Amplifying Guidance for Hallucination-Resistant Sampling
Hyunmin Cho, Donghoon Ahn, Susung Hong +3
Diffusion models achieve state-of-the-art image generation but often produce semantic inconsistencies, or hallucinations. Existing inference-time guidance methods rely on external…