activity
20232026
most citedKoMultiText: Large-Scale Korean Text Dataset for Classifying Biased Speech in Real-World Online Services

1 citations · 2 across the 8 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

Do Safety Guardrails Need to Reason? LeanGuard: A Fast and Light Approach for Robust Moderation

Dongbin Na

In order to screen a prompt or a response, the recent guardrail methods generate a chain-of-thought (CoT) before they issue a verdict. This design follows a common belief that step…