30 papers
One Adapter Pair per Model: A Universal Activation Interface for Language Models
Su-Hyeon Kim, Jiwan Mun, Yo-Sub Han
Activation-based tools are usually tied to one model's native hidden space, requiring probes, sparse autoencoders, and natural-language interpreters to be rebuilt or rediscovered f…
EPIC: Efficient and Parallel Inference under CFG Constraints for Diffusion Language Models
Hyundong Jin, Yo-Sub Han
Controlling language model outputs is essential for ensuring structural validity, reliability, and downstream usability, and diffusion language models are no exception. Recent adva…
Linguistics-Aware Non-Distortionary LLM Watermarking
Shinwoo Park, Hyejin Park, Hyeseon An +1
Watermarking should identify language-model output without degrading quality or limiting verification to the model provider. Multilingual deployment makes this harder because morph…
DLM-SWAI: Steering Diffusion Language Models Before They Unmask
Hyeseon An, Yo-Sub Han
Steering language model generation toward desired textual properties is essential for practical deployment, and inference-time methods are particularly appealing because they enabl…
Steering Language Models Before They Speak: Logit-Level Interventions
Hyeseon An, Shinwoo Park, Hyundong Jin +1
Controllable generation requires language models to realize output characteristics such as reading level, politeness, and toxicity. Existing steering methods are often indirect, re…
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…