Papers by Dang Nguyen

VlogQA: Task, Dataset, and Baseline Models for Vietnamese Spoken-Based Machine Reading Comprehension (2024.eacl-long)

Copied to clipboard

Thinh Ngo, Khoa Dang, Son Luu, Kiet Nguyen, Ngan Nguyen

Challenge:	Existing datasets for machine reading comprehension tasks in Vietnamese focus on written documents, such as Wikipedia articles, online newspapers, or textbooks.
Approach:	They propose to capture Vietnamese spoken language in natural settings and use it to create a machine-learning corpus for machine reading comprehension tasks.
Outcome:	The proposed corpus consists of 10,076 question-answer pairs based on 1,230 transcript documents sourced from YouTube .

Aurora-M: Open Source Continual Pre-training for Multilingual Language and Code (2025.coling-industry)

Copied to clipboard

Taishi Nakamura, Mayank Mishra, Simone Tedeschi, Yekun Chai, Jason T. Stillerman, Felix Friedrich, Prateek Yadav, Tanmay Laud, Vu Minh Chien, Terry Yue Zhuo, Diganta Misra, Ben Bogin, Xuan-Son Vu, Marzena Karpinska, Arnav Varma Dantuluri, Wojciech Kusa, Tommaso Furlanello, Rio Yokota, Niklas Muennighoff, Suhas Pai, Tosin Adewumi, Veronika Laippala, Xiaozhe Yao, Adalberto Barbosa Junior, Aleksandr Drozd, Jordan Clive, Kshitij Gupta, Liangyu Chen, Qi Sun, Ken Tsui, Nour Moustafa-Fahmy, Nicolo Monti, Tai Dang, Ziyang Luo, Tien-Tung Bui, Roberto Navigli, Virendra Mehta, Matthew Blumberg, Victor May, Hiep Nguyen, Sampo Pyysalo

Language Models

Challenge:	Pretrained language models are integral part of AI applications, but their high computational cost limits accessibility.
Approach:	They evaluate Aurora-M, a 15B parameter multilingual open-source model trained on English, Finnish, Hindi, Japanese, Vietnamese, and code.
Outcome:	The proposed model outperforms existing models on English, Finnish, Hindi, Japanese, Vietnamese, and code.

RuleR: Improving LLM Controllability by Rule-based Data Recycling (2025.naacl-short)

Copied to clipboard

Ming Li, Han Chen, Chenguang Wang, Dang Nguyen, Dianqi Li, Tianyi Zhou

Challenge:	Existing supervised fine-tuning datasets are composed of general instructions without userspecified constraints.
Approach:	They propose a data augmentation method incorporating multiple constraints into the original data samples according to predefined rules to create new training tasks.
Outcome:	The proposed method improves LLM controllability while maintaining general instruction-following capabilities.

Beyond Semantic Entropy: Boosting LLM Uncertainty Quantification with Pairwise Semantic Similarity (2025.findings-acl)

Copied to clipboard

Dang Nguyen, Ali Payani, Baharan Mirzasoleiman

Text Clustering

Challenge:	Large Language Models (LLMs) generate long one-sentence responses that are less effective because they overlook two crucial factors: intra-cluster similarity and inter-c cluster similarity.
Approach:	They propose a method that generalizes semantic entropy and uses token probabilities to quantify uncertainty in large language models.
Outcome:	The proposed method can be extended to white-box settings by incorporating token probabilities.

OZSpeech: One-step Zero-shot Speech Synthesis with Learned-Prior-Conditioned Flow Matching (2025.acl-long)

Copied to clipboard

Nghia Huynh Nguyen Hieu, Ngoc Son Nguyen, Huynh Nguyen Dang, Thieu Vo, Truong-Son Hy, Van Nguyen

Multimodality

Challenge:	Text-to-speech systems have seen significant advances in recent years, driven by improvements in deep learning and neural network architectures.
Approach:	They propose a method to explore optimal transport conditional flow matching with one-step sampling and a learned prior as the condition, effectively disregarding preceding states and reducing the number of sampling steps.
Outcome:	The proposed method achieves promising performance over existing methods in content accuracy, naturalness, prosody generation, and speaker style preservation.

Multi-Dialect Vietnamese: Task, Dataset, Baseline Models and Challenges (2024.emnlp-main)

Copied to clipboard

Nguyen Dinh, Thanh Dang, Luan Thanh Nguyen, Kiet Nguyen

Multimodality

Challenge:	Vietnamese is a low-resource language, but each province has its own distinct pronunciation variations.
Approach:	They propose a dataset that captures the rich diversity of 63 provincial dialects spoken in Vietnam.
Outcome:	The proposed dataset captures the rich diversity of 63 provincial dialects spoken across Vietnam.

GPT-4V Cannot Generate Radiology Reports Yet (2025.findings-naacl)

Copied to clipboard

Yuyang Jiang, Chacha Chen, Dang Nguyen, Benjamin M. Mervak, Chenhao Tan

Language Models

Challenge:	Large language models (LLMs) are becoming multimodal, and GPT-4 models are supposed to possess advanced skills across a wide range of domains, including high-stakes scenarios such as medicine.
Approach:	They perform a systematic evaluation of GPT-4 in generating radiology reports across three chest X-ray report benchmarks: MIMIC-CXR, CheXpert Plus, and IU X ray.
Outcome:	The proposed model fails in lexical and clinical efficacy metrics . the distributions of model-predicted labels remain constant regardless of groundtruth conditions on the image, suggesting that the model is not interpreting chest X-rays meaningfully.

Multi-Objective Linguistic Control of Large Language Models (2024.findings-acl)

Copied to clipboard

Dang Nguyen, Jiuhai Chen, Tianyi Zhou

Semantic Text Processing

Challenge:	Existing Large language models prefer to generate verbose responses due to the length bias, which may increase unnecessary reading complexity.
Approach:	They propose to use off-the-shelf data to fine tune multiple linguistic complexities of LLM outputs to improve multi-complexity controllability and improve the quality of the responses.
Outcome:	The proposed method improves multi-complexity controllability significantly and retains or enhances the quality of the responses as a side benefit.

Class based Influence Functions for Error Detection (2023.acl-short)

Copied to clipboard

Thang Nguyen-Duc, Hoang Thanh-Tung, Quan Hung Tran, Dang Huu-Tien, Hieu Nguyen, Anh T. V. Dau, Nghi Bui

Responsible & Trustworthy NLP

Challenge:	Influence functions (IFs) are powerful tools for detecting anomalous examples in large scale datasets.
Approach:	They propose a method to explain the instability of IFs by leveraging class information to improve the stability of ifs.
Outcome:	The proposed method improves performance and stability while incurring no additional computational cost.

Introducing a Large-Scale Dataset for Vietnamese POS Tagging on Conversational Texts (2020.lrec-1)

Copied to clipboard

Oanh Tran, Tu Pham, Vu Dang, Bang Nguyen

Dialogue Systems & Conversational Agents

Challenge:	POS taggers are trained on informal texts which contain many informal inputs such as acronyms, abbreviations, out-of-vocabulary words, etc.
Approach:	They propose a large-scale human-labeled dataset for the Vietnamese POS tagging task on conversational texts and develop an annotation guideline to manually annotate 16.310K sentences using this guideline.
Outcome:	The proposed tagging scheme achieved 93.36% accuracy score and higher than the model with handcrafted features and fine-tuning BERT.

GUI Agents: A Survey (2025.findings-acl)

Copied to clipboard

Dang Nguyen, Jian Chen, Yu Wang, Gang Wu, Namyong Park, Zhengmian Hu, Hanjia Lyu, Junda Wu, Ryan Aponte, Yu Xia, Xintong Li, Jing Shi, Hongjie Chen, Viet Dac Lai, Zhouhang Xie, Sungchul Kim, Ruiyi Zhang, Tong Yu, Mehrab Tanjim, Nesreen K. Ahmed, Puneet Mathur, Seunghyun Yoon, Lina Yao, Branislav Kveton, Jihyung Kil, Thien Huu Nguyen, Trung Bui, Tianyi Zhou, Ryan A. Rossi, Franck Dernoncourt

Challenge:	Large Foundation Models (LFMs) have transformed the landscape of AI research and day-to-day life.
Approach:	They propose a framework that delineates GUI agents' perception, reasoning, planning, and acting capabilities.
Outcome:	The proposed framework delineates their perception, reasoning, planning, and acting capabilities.

Improving Chain-of-Thought for Logical Reasoning via Attention-Aware Intervention (2026.findings-eacl)

Copied to clipboard

Phuong Minh Nguyen, Dang Huu-Tien, Naoya Inoue

Low-Resource NLP

Challenge:	Modern logical reasoning with LLMs relies on employing complex interactive frameworks that decompose the reasoning process into subtasks solved through carefully designed prompts or requiring external components, which limit their scalability.
Approach:	They propose a non-interactive, end-to-end framework for reasoning tasks that enables reasoning to emerge within the model itself.
Outcome:	The proposed framework improves generalization while preserving analyzability without external resources.

Conversation Understanding using Relational Temporal Graph Neural Networks with Auxiliary Cross-Modality Interaction (2023.emnlp-main)

Copied to clipboard

Cam Van Thi Nguyen, Tuan Mai, Son The, Dang Kieu, Duc-Trong Le

Multimodality

Challenge:	Emotion recognition is a crucial task for human conversation understanding . multimodal data, e.g., language, voice, and facial expressions, add complexity to the task.
Approach:	They propose a relational temporal Graph Neural Network with Auxiliary Cross-Modality Interaction framework that captures conversation-level cross-modality interactions and utterance-level temporal dependencies with modality-specific manner for conversation understanding.
Outcome:	The proposed framework captures conversation-level cross-modality interactions and utterance-level temporal dependencies with the modality-specific manner for conversation understanding.