← Search

Sihyeon Park

2 accepted papers

2025

Learning from Negative Samples in Biomedical Generative Entity Linking

ACL 2025finding

Generative models have become widely used in biomedical entity linking (BioEL) due to their excellent performance and efficient memory usage. However, these models are usually trained only with positive samples—entities that match the input mention’s identifier—and do not explicitly learn from hard…

2025

Rationale-Guided Retrieval Augmented Generation for Medical Question Answering

NAACL 2025long

Large language models (LLM) hold significant potential for applications in biomedicine, but they struggle with hallucinations and outdated knowledge.While retrieval-augmented generation (RAG) is generally employed to address these issues, it also has its own set of challenges: (1) LLMs are vulnerabl…