3 papers
cs.IR2026
Ruling Out to Rule In: Contrastive Hypothesis Retrieval for Medical Question Answering
Byeolhee Kim, Min-Kyung Kim, Young-Hak Kim +1
Retrieval-augmented generation (RAG) grounds large language models in external medical knowledge, yet standard retrievers frequently surface hard negatives that are semantically cl…
cs.CV2024
Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation
Minkyoung Kim, Yunha Kim, Hyeram Seo +9
Large language models (LLMs) have exhibited outstanding performance in natural language processing tasks. However, these models remain susceptible to adversarial attacks in which s…
cs.CL2024
Enhancing Clinical Efficiency through LLM: Discharge Note Generation for Cardiac Patients
HyoJe Jung, Yunha Kim, Heejung Choi +10
Medical documentation, including discharge notes, is crucial for ensuring patient care quality, continuity, and effective medical communication. However, the manual creation of the…