5 papers
SchurQuant: Groupwise Discrete Optimization for Layer-Wise LLM Quantization
Gunjun Lee, Sehwan Son, Younjoo Lee +2
Weight-only post-training quantization (PTQ) enables the deployment of large language models under tight memory budgets, but accuracy often collapses at 2-3 bits. Existing backprop…
PHISH in MESH: Korean Adversarial Phonetic Substitution and Phonetic-Semantic Feature Integration Defense
Byungjun Kim, Minju Kim, Hyeonchu Park +1
As malicious users increasingly employ phonetic substitution to evade hate speech detection, researchers have investigated such strategies. However, two key challenges remain. Firs…
DART: An AIGT Detector using AMR of Rephrased Text
Hyeonchu Park, Byungjun Kim, Bugeun Kim
As large language models (LLMs) generate more human-like texts, concerns about the side effects of AI-generated texts (AIGT) have grown. So, researchers have developed methods for…
Leveraging Large Language Models for Active Merchant Non-player Characters
Byungjun Kim, Minju Kim, Dayeon Seo +1
We highlight two significant issues leading to the passivity of current merchant non-player characters (NPCs): pricing and communication. While immersive interactions with active N…
Fine-Grained and Thematic Evaluation of LLMs in Social Deduction Game
Byungjun Kim, Dayeon Seo, Minju Kim +1
Recent studies have investigated whether large language models (LLMs) can support obscured communication, which is characterized by core aspects such as inferring subtext and evadi…