5 papers
PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization
Boryeong Cho, Sumyeong Ahn, Se-Young Yun
Direct Preference Optimization (DPO) simplifies alignment through pairwise comparisons but assumes all observed preferences are reliable. Real data often violates this assumption,…
Rethinking Personalized Reward Modeling for LLMs under Preference Heterogeneity via Group-Debiased Federated Learning
Seongyoon Kim, Boryeong Cho, Jihwan Oh +2
Large language models are increasingly aligned to human preferences via reward modeling, but user preference data are sensitive and often cannot be centralized. Federated learning…
UniSAFE: A Comprehensive Benchmark for Safety Evaluation of Unified Multimodal Models
Segyu Lee, Boryeong Cho, Hojung Jung +8
Unified Multimodal Models (UMMs) offer powerful cross-modality capabilities but introduce new safety risks not observed in single-task models. Despite their emergence, existing saf…
Stage-wise Attention-Guided Region Sequencing for Adversarial Attacks on Large Vision-Language Models
Jaehyun Kwak, Nam Cao, Boryeong Cho +3
Targeted adversarial attacks on Large Vision-Language Models (LVLMs) test whether small image perturbations can steer model responses toward attacker-specified content. Under the s…
VACoDe: Visual Augmented Contrastive Decoding
Sihyeon Kim, Boryeong Cho, Sangmin Bae +2
Despite the astonishing performance of recent Large Vision-Language Models (LVLMs), these models often generate inaccurate responses. To address this issue, previous studies have f…