Publications

I am an early-stage researcher working at the intersection of theory and practice in modern NLP systems. My work is driven by the goal of building research artifacts that are scientifically rigorous, empirically sound, and practically grounded, with careful evaluation across diverse real-world scenarios. I actively work toward producing high-quality research contributions and contributing to the NLP community through publications at leading international venues.

2026
  1. Quy T. Nguyen*, Long S. T. Nguyen*, and Tho T. Quan. Morphological Strategies of Word Formation in Bahnar: A Study of Prefixes and Infixes. Taiwan Journal of Linguistics, 2026. (ESCI, Q3)
  2. Mao Nguyen, Thien Pham, Long S. T. Nguyen, Dang Le, Trung M. Pham, Hieu M. Pham, Duc Q. Nguyen, Xinh Le, Anh H. Huynh, Triet T. M. Le, and Tho T. Quan. Conceptual Relationship Between Classical Machine Learning and Graph Neural Networks in Out-of-Distribution Detection: A Comprehensive Survey. IEEE Access, 2026. (SCIE, Q1)
  3. Long S. T. Nguyen, Tin T. Ngo, Dung N. H. Le, Quynh T. N. Vo, Dung H. Nguyen, Khang N. Le, and Tho T. Quan. A Benchmark for Structured Multihop Reasoning in Cross-Institution University Admission Advisory Question Answering. Workshop on Autonomous Machine Intelligence: From Theory to Practice (AMI), at PAKDD, 2026. (Workshop at B-ranked Conference)
  4. Quoc Phu Dang*, Phat T. Tran-Truong*, Duc-Ly Vu, Long S. T. Nguyen, Quynh T. N. Vo, and Tho T. Quan. Enhancing Large Language Model Performance for Automatic Zero-Shot Multiple-Choice Question Answering via Single-Token Logit Prompting. Computers and Education: Artificial Intelligence, 2026. (SCIE, Q1, #1 in Education) [pdf] [bib] [website]
  5. Long S. T. Nguyen*, Quan M. Bui*, Tin T. Ngo, Quynh T. N. Vo, Dung N. H. Le, and Tho T. Quan. ViHERMES: A Graph-Grounded Multihop Question Answering Benchmark and System for Vietnamese Healthcare Regulations. Asian Conference on Intelligent Information and Database Systems (ACIIDS), 2026. (B-ranked Conference) (Best Student Paper Nomination) [pdf] [bib] [website]
  6. Long S. T. Nguyen and Tho T. Quan. Which Works Best for Vietnamese? A Practical Study of Information Retrieval Methods across Domains. Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2026. (A-ranked Conference) [pdf] [bib] [website]
  7. Hung Luu, Long S. T. Nguyen, Trung Pham, Hieu Pham, and Tho Quan. HiGraAgent: Dual-Agent Adaptive Reasoning over Hierarchical Knowledge Graph for Open-Domain Multi-hop Question Answering. Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2026. (A-ranked Conference) [pdf] [bib] [website]
  8. Long Nguyen, Duc Nguyen, Quan Bui, Dung Phan, Dung Le, Khanh Nguyen, Quynh Vo, Khang Vo, Nam Duong, Anh Dinh, Tri Trinh, Chi Phan, An Nguyen, Thai Nguyen, Dang Le, Vinh Dang, and Tho Quan. Catching the First Light of Tomorrow: A Hackathon-Based Framework for Introducing High School Students to AI Agents. AAAI Conference on Artificial Intelligence (AAAI), 2026. (A*-ranked Conference) [pdf] [bib] [website]
  9. Dung T. Phan*, Chi N. L. Phan*, Long S. T. Nguyen*, Phuc T. Dao, Quan M. Bui, Tin T. Ngo, Thi T. Nguyen, and Tho T. Quan. MAFIA-NeT: Multi-Agent Framework for Interactive Agricultural Negotiation and Trading Systems. International Conference on Agents and Artificial Intelligence (ICAART), 2026. (B-ranked Conference) (Selected for Post-Publication) [pdf] [bib] [website]
2025
  1. Long S. T. Nguyen, Quynh T. N. Vo, Thi T. Nguyen, and Tho T. Quan. URAG 2.0: An Agentic Dual Retrieval Framework for Enhanced Reasoning in RAG-based QA Systems. Symposium on Information and Communication Technology (SoICT), 2025.
  2. Tai Q. To*, Long S. T. Nguyen*, Hung C. Nguyen, Nguyen B. Le, Tam M. Nguyen, Tung T. Nguyen, Chattrakul Sombattheera, and Tho T. Quan. AI Conferences Made Easy by AI - A Case Study at MIWAI 2025. IEEE-RIVF International Conference on Computing and Communication Technologies (RIVF), 2025. [pdf] [bib] [website]
  3. Long S. T. Nguyen, Quynh T. N. Vo, Hung C. Luu, and Tho T. Quan. When in Doubt, Ask First: A Unified Retrieval Agent-Based System for Ambiguous and Unanswerable Question Answering. International Joint Conference on Natural Language Processing & Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL), 2025. (B-ranked Conference) [pdf] [bib] [website]
  4. Long S. T. Nguyen, Hung C. Luu, Quynh T. N. Vo, Hy N. G. La, Hoai M. Tran, Anh T. D. Dinh, Tuan H. Nguyen, Tri N. Ho, and Tho T. Quan. Can Small Language Models Handle Vietnamese Legal Reasoning? Insights from Multi-Task Evaluation. Workshop on Vietnamese Language and Speech Processing (VLSP), at INLG, 2025. [pdf] [bib] [website]
  5. Long S. T. Nguyen*, Khang H. N. Vo*, Thu H. A. Nguyen*, Tuan C. Bui, Duc Q. Nguyen, Thanh-Tung Tran, Anh D. Nguyen, Minh L. Nguyen, Fabien Baldacci, Thang H. Bui, Emanuel Di Nardo, Angelo Ciaramella, Son H. Le, Ihsan Ullah, Lorenzo Di Rocco, and Tho T. Quan. Bridging LLMs and Symbolic Reasoning in Educational QA Systems: Insights from the XAI Challenge at IJCNN 2025. Italian Conference on Big Data and Data Science (ITADATA), 2025. [pdf] [bib] [website]
  6. Tuan Bui, An Nguyen, Phat Thai, Minh Hua, Ngan L. N. Pham, Ngan T. B. Pham, Dung Le, Long Nguyen, Thanh-Tung Tran, Thang Bui, and Tho Quan. Formal Reasoning for Intelligent QA Systems: A Case Study in the Educational Domain. ACM Workshop on AI-powered Question & Answering Systems (AIQAM), at ACMMM, 2025. ️(Workshop at A*-ranked Conference) [pdf] [bib] [website]
  7. Long S. T. Nguyen, Truong P. Hua, Thanh M. Nguyen, Toan Q. Pham, Nam K. Ngo, An X. Nguyen, Nghi D. M. Pham, Nghia H. Nguyen, and Tho T. Quan. A Benchmark Dataset and Evaluation Framework for Vietnamese Large Language Models in Customer Support. International Conference on Computational Collective Intelligence (ICCCI), 2025. (B-ranked Conference) [pdf] [bib] [website]
  8. Duc Nguyen, Dong Le, Long Nguyen, Quyen Vu, Tran Le, Dung Nguyen, Nga Huynh, Huong Nguyen, Phat Tran, Dang Le, Sang Truong, Sanmi Koyejo, Cuong Le, and Tho Quan. Riding on The Back of A Whale: A Hackathon Framework for Introducing High School Students to Large Language Models. Conference on Artificial Intelligence in Education (AIED), 2025. (A-ranked Conference) [pdf] [bib] [website]
  9. Long S. T. Nguyen, Tran T. B. Le, Huong P. N. Nguyen, Quynh T. N. Vo, Phong H. N. Nguyen, and Tho T. Quan. Serving the Underserved: Leveraging BARTBahnar Language Model for Bahnaric-Vietnamese Translation. Workshop on Language Models for Underserved Communities (LM4UC), at NAACL, 2025. (Workshop at A-ranked Conference) [pdf] [bib] [website]
2024
  1. Long S. T. Nguyen and Tho T. Quan. URAG: Implementing a Unified Hybrid RAG for Precise Answers in University Admission Chatbots – A Case Study at HCMUT. Symposium on Information and Communication Technology (SoICT), 2024. [pdf] [bib] [website]
  2. Long S. T. Nguyen*, Huy G. Nguyen*, Bao G. Khuu, Huy A. T. Luu, Huy Q. Le, Tuan T. Nguyen, and Tho T. Quan. RAPID: Retrieval-Augmented Parallel Inference Drafting for Text-Based Video Event Retrieval. Symposium on Information and Communication Technology (SoICT), 2024. [pdf] [bib] [website]
  3. Tuan Bui, Oanh Tran, Phuong Nguyen, Bao Ho, Long Nguyen, Thang Bui, and Tho Quan. Cross-Data Knowledge Graph Construction for LLM-enabled Educational Question-Answering System: A Case Study at HCMUT. ACM Workshop on AI-Powered Q&A Systems for Multimedia (AIQAM), at ICMR, 2024. [pdf] [bib] [website]
non-archival
  1. Long S. T. Nguyen, Dat T. Truong, Nhan D. Tran, Quynh T. N. Vo, Quy T. Nguyen, and Tho T. Quan. Not All Data Augmentation Works: A Typology-Aware Study for Low-Resource Neural Machine Translation in Vietnamese Ethnic Minority Languages. Workshop on Language Models for Underserved Communities (LM4UC), at AAAI, 2026. (Workshop at A*-ranked Conference) [pdf] [bib] [website]
  2. Thi Ty Nguyen, Phat T. Tran-Truong, Long S. T. Nguyen, Tan Sang Nguyen, and Tho T. Quan. Sentence-Aware Bahnaric-Vietnamese Lexical Mapping with Contrastive Contextual Representations. Workshop on Language Models for Underserved Communities (LM4UC), at AAAI, 2026. (Workshop at A*-ranked Conference) [pdf] [bib] [website]