collaborators

6 papers

cs.CL2026

Obfuscation Rules for Detecting and Detoxifying Korean Toxicity

Yejin Lee, Su-Hyeon Kim, Hyundong Jin +3

As language models become increasingly deployed in online environments, toxicity detection and detoxification have received growing attention. Existing studies primarily focus on n…

cs.AI2026

CRaFT: Circuit-Guided Refusal Feature Selection via Cross-Layer Transcoders

Su-Hyeon Kim, Hyundong Jin, Yejin Lee +1

While modern LLMs are aligned to refuse harmful requests, it is essential to understand the underlying mechanistic basis of this refusal behavior for model safety analysis. For exa…

cs.CL2026

Adaptive Steering and Remasking for Safe Generation in Diffusion Language Models

Yejin Lee, Yo-Sub Han

Diffusion Language Models (DLMs) provide a promising alternative to autoregressive language models by generating text through iterative denoising and bidirectional refinement. Howe…

cs.CL2026

RV-HATE: Reinforced Multi-Module Voting for Implicit Hate Speech Detection

Yejin Lee, Hyeseon Ahn, Yo-Sub Han

Hate speech remains prevalent in human society and continues to evolve in its forms and expressions. Modern advancements in internet and online anonymity accelerate its rapid sprea…

cs.AI2026

How Does the Thinking Step Influence Model Safety? An Entropy-based Safety Reminder for LRMs

Su-Hyeon Kim, Hyundong Jin, Yejin Lee +1

Large Reasoning Models (LRMs) achieve remarkable success through explicit thinking steps, yet the thinking steps introduce a novel risk by potentially amplifying unsafe behaviors.…

cs.CL2025

AmpleHate: Amplifying the Attention for Versatile Implicit Hate Detection

Yejin Lee, Joonghyuk Hahn, Hyeseon Ahn +1

Implicit hate speech detection is challenging due to its subtlety and reliance on contextual interpretation rather than explicit offensive words. Current approaches rely on contras…