6 papers
Evidence-Consistent Generative Detection under Scenario-Level Distribution Shift
San Kim, JinYeong Bak
Conventional in-distribution evaluation can overestimate robustness when training and test data share recurring task-specific patterns or surface cues. This risk is especially rele…
Merging Triggers, Breaking Backdoors: Defensive Poisoning for Instruction-Tuned Language Models
San Kim, Gary Geunbae Lee
Large Language Models (LLMs) have greatly advanced Natural Language Processing (NLP), particularly through instruction tuning, which enables broad task generalization without addit…
PanicToCalm: A Proactive Counseling Agent for Panic Attacks
Jihyun Lee, Yejin Min, San Kim +4
Panic attacks are acute episodes of fear and distress, in which timely, appropriate intervention can significantly help individuals regain stability. However, suitable datasets for…
Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection
San Kim, Jonghwi Kim, Yejin Jeon +1
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by providing external knowledge for accurate and up-to-date responses. However, this reliance on external…
Enhancing Dialogue Speech Recognition with Robust Contextual Awareness via Noise Representation Learning
Wonjun Lee, San Kim, Gary Geunbae Lee
Recent dialogue systems rely on turn-based spoken interactions, requiring accurate Automatic Speech Recognition (ASR). Errors in ASR can significantly impact downstream dialogue ta…
Adversarial DPO: Harnessing Harmful Data for Reducing Toxicity with Minimal Impact on Coherence and Evasiveness in Dialogue Agents
San Kim, Gary Geunbae Lee
Recent advancements in open-domain dialogue systems have been propelled by the emergence of high-quality large language models (LLMs) and various effective training methodologies.…