Author

Sungwon Chae

h-index 1 View on Semantic Scholar

We have 2 of 3 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Open access Sep 2026

Cross‐lingual safety asymmetry in open‐weight LLMs

Safety alignment in large language models is overwhelmingly trained on English data, yet models are deployed across typologically diverse languages. We evaluate six open‐weight large language models (LLMs) across 17 bilingual Korean/Chinese prompt conditions and three translation engines (NLLB‐200, Gemini 3.0 Pro, an...

Sungwon Chae, Younghwan Gil · ETRI Journal · 0 citations

#artificial intelligence Preprint Jun 2026

Position: Current Model Cards Are Insufficient for Downstream Governance of Open-Weight Foundation Models

It is argued that effective governance of OWFMs requires a multi-layered approach integrating three complementary components: model cards, acceptable use policies (AUPs), and licenses, and that standard open-source licenses are not well suited for OWFMs and may weaken the enforceability of AUPs.

Sungwon Chae, Keonwoo Kim, Hoki Kim et al. · 0 citations