Wonjune Jang

A novel LLM framework that adapts inference strategies based on question type leads to superior performance in biomedical question answering, clinching first place in a competitive evaluation.

Scientific figure QA models are often fooled by the answer choices themselves, but a simple decoding strategy that contrasts image-grounded scores with text-only scores can significantly improve accuracy.

Small language models can achieve surprisingly robust question answering by actively clustering their memories into semantically coherent groups, outperforming standard retrieval methods.