Khai-Nguyen Nguyen — accepted AI-conference papers

2026

Vision Language Models are Biased

An Vo, Khai-Nguyen Nguyen, Mohammad Reza Taesiri, Vy Tuong Dang, Anh Totti Nguyen, Daeyoung Kim

ICLR 2026poster

Large language models (LLMs) memorize a vast amount of prior knowledge from the Internet that helps them on downstream tasks but also may notoriously sway their outputs towards wrong or biased answers. In this work, we test how the knowledge about popular subjects hurt the accuracy of vision languag…

Cited by 0 Source ↗code ↗Scholar ↗

2025

Medical Spoken Named Entity Recognition

Khai Le-Duc, David Thulke, Hung-Phong Tran, Long Vo-Dang, Khai-Nguyen Nguyen, Truong-Son Hy +1

NAACL 2025industry

Spoken Named Entity Recognition (NER) aims to extract named entities from speech and categorise them into types like person, location, organization, etc. In this work, we present *VietMed-NER* - the first spoken NER dataset in the medical domain. To our knowledge, our Vietnamese real-world dataset i…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗