10 papers
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…
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…
STAB: Specification-driven Testing for Algorithmic Bottlenecks
Soohan Lim, Joonghyuk Hahn, Hyundong Jin +1
Evaluating the efficiency of algorithmic code requires test cases that expose runtime bottlenecks. Previous methods generate efficiency test cases either by increasing input size o…
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…
NCO: A Versatile Plug-in for Handling Negative Constraints in Decoding
Hyundong Jin, Yo-Sub Han
Controlling Large Language Models (LLMs) to prevent the generation of undesirable content, such as profanity and personally identifiable information (PII), has become increasingly…