6 papers
Look Before You Leap: Factual Decoding with Internal Attribution Signals
Hayeong Ryu, JungMin Yun, Byeonggeuk Lim +2
Hallucination remains a critical challenge in large language models (LLMs), where early factual errors compound through autoregressive generation in a snowballing effect that neith…
Beyond Safe Answers: Segment-Aware Listwise Alignment for Reasoning Safety in Large Reasoning Models
JungMin Yun, Junehyoung Kwon, Hayeong Ryu +3
Large Reasoning Models (LRMs) pose a dual-surface safety challenge: both intermediate reasoning traces and final answers can contain harmful content. Existing alignment methods oft…
ALTSTEER: Selective Safety Steering for Moving Beyond Hard Refusals to Constructive Alternatives
Hoejoon Kwon, Byeonggeuk Lim, Kahyeon Kim +1
Safety alignment is essential for deploying large language models, requiring systems to prevent harmful compliance while preserving helpfulness on benign requests. Activation steer…
Before Forgetting, Learn to Remember: Revisiting Foundational Learning Failures in LVLM Unlearning Benchmarks
JuneHyoung Kwon, MiHyeon Kim, Eunju Lee +3
While Large Vision-Language Models (LVLMs) offer powerful capabilities, they pose privacy risks by unintentionally memorizing sensitive personal information. Current unlearning ben…
Aligning with Your Own Voice: Self-Corrected Preference Learning for Hallucination Mitigation in LVLMs
Byeonggeuk Lim, JungMin Yun, Junehyoung Kwon +2
Large Vision-Language Models (LVLMs) frequently suffer from hallucinations. Existing preference learning-based approaches largely rely on proprietary models to construct preference…
VG-CoT: Towards Trustworthy Visual Reasoning via Grounded Chain-of-Thought
Byeonggeuk Lim, Kyeonghyun Kim, JungMin Yun +1
The advancement of Large Vision-Language Models (LVLMs) requires precise local region-based reasoning that faithfully grounds the model's logic in actual visual evidence. However,…