8 papers
Prune Once: Retraining-Free Task-Agnostic Pruning for Vision-Language Models
Minseok Kang, Hyunwoo Kim, Chanyoung Kim +3
Vision-language models (VLMs) have achieved remarkable generalization across diverse multimodal tasks through large-scale pre-training, yet their rapidly increasing computational a…
FinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming
Chaeyun Kim, Daeyoung Park, Junghwan Kim +4
Existing safety benchmarks target general adversarial scenarios but miss finance-specific risks. Financial LLMs face regulatory compliance violations, fraud facilitation, and syste…
Culturally-Adapted Red-Teaming Across East and Southeast Asian Contexts: A Methodological and Comparative Analysis
Hyeji Choi, Yongtaek Lim, Minwoo Kim
Multilingual safety evaluation of large language models (LLMs) has predominantly relied on direct translation (DT) of English benchmarks into target languages - an approach that co…
Reliable to Expressive: A Curriculum for Rubric-Following Safety Judges
Yongtaek Lim, Hyeji Choi, Minwoo Kim
Safety judges are increasingly deployed to evaluate model outputs against evolving criteria, yet recent meta-evaluation work shows they remain brittle under prompt and rubric varia…
Korean Culture into LLM Alignment: Toward Cultural Coherence
MinJae Jung, Minwoo Kim
Cultural-aspect work on large language models is dominated by a negative target: which outputs to suppress. We argue that a constructive counterpart is also needed, a working defin…
STAR-Teaming: A Strategy-Response Multiplex Network Approach to Automated LLM Red Teaming
MinJae Jung, YongTaek Lim, Chaeyun Kim +3
While Large Language Models (LLMs) are widely used, they remain susceptible to jailbreak prompts that can elicit harmful or inappropriate responses. This paper introduces STAR-Team…