Ha-Thanh Nguyen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ha-Thanh Nguyen has a total of 121 co-authors. Here are the top co-authors by number of shared publications:
- Ken Satoh
Center for Juris-Informatics, ROIS-DS, Tokyo, Japan
18 shared publications - Le-Minh Nguyen
Information Science, Japan Advanced Institute of Science and Technology, Nomi, Japan
15 shared publications - Thi-Hai-Yen Vuong
VNU University of Engineering and Technology, Hanoi, Vietnam
10 shared publications Ken Satoh
8 shared publications- May Myo Zin
Center for Juris-Informatics, ROIS-DS, Tokyo, Japan
7 shared publications Thi-Hai-Yen Vuong
VNU University of Engineering and Technology Hanoi Vietnam
7 shared publications
Latest Publications
- 17 November 2026
- Published by Springer Nature
- p. 133-148
Beyond Vision-Language Models: Visual-Semantic Affect Graphs for Emotion Recognition in Artworks
- 17 November 2026
- Published by Springer Nature
- p. 133-148
Beyond Vision-Language Models: Visual-Semantic Affect Graphs for Emotion Recognition in Artworks
- 6 June 2026
- Published by Springer Nature
- p. 18-32
Resolving Definitional Ambiguity in Legal Language: A Logical Approach to Consistent Judicial Outcomes
- 6 June 2026
- Published by Springer Nature
- p. 18-32
Resolving Definitional Ambiguity in Legal Language: A Logical Approach to Consistent Judicial Outcomes
- 6 June 2026
- Published by Springer Nature
- p. 115-130
Improving Reliability in Multimodal Legal Interpretation of Traffic Signs
- 6 June 2026
- Published by Springer Nature
- p. 115-130
Improving Reliability in Multimodal Legal Interpretation of Traffic Signs
- Open Access
Argumentative Reasoning with Language Models on Non-factorized Case Bases
In this paper, we investigate how language models can perform case-based reasoning (CBR) on non-factorized case bases. We introduce a novel framework, argumentative agentic models for case-based reasoning (AAM-CBR), which extends abstract argumentation for case-based reasoning (AA-CBR). Unlike traditional approaches that require factorization of previous cases, AAM-CBR leverages language models to determine case coverage and extract factors based on new cases. This enables factor-based reasoning without exposing or preprocessing previous cases, thus improving both flexibility and privacy. We also present initial experiments to assess AAM-CBR performance by comparing the proposed framework with a baseline that uses a single-prompt approach to incorporate both new and previous cases. The experiments are conducted based on a synthetic credit card application dataset. The result shows that AAM-CBR surpasses the baseline only when the new case contains a richer set of factors. The finding indicates that language models can handle case-based reasoning with a limited number of factors, but face challenges as the number of factors increase. Consequently, integrating symbolic reasoning with language models, as implemented in AAM-CBR, is crucial for effectively handling cases involving many factors.
Open AccessArgumentative Reasoning with Language Models on Non-factorized Case Bases
In this paper, we investigate how language models can perform case-based reasoning (CBR) on non-factorized case bases. We introduce a novel framework, argumentative agentic models for case-based reasoning (AAM-CBR), which extends abstract argumentation for case-based reasoning (AA-CBR). Unlike traditional approaches that require factorization of previous cases, AAM-CBR leverages language models to determine case coverage and extract factors based on new cases. This enables factor-based reasoning without exposing or preprocessing previous cases, thus improving both flexibility and privacy. We also present initial experiments to assess AAM-CBR performance by comparing the proposed framework with a baseline that uses a single-prompt approach to incorporate both new and previous cases. The experiments are conducted based on a synthetic credit card application dataset. The result shows that AAM-CBR surpasses the baseline only when the new case contains a richer set of factors. The finding indicates that language models can handle case-based reasoning with a limited number of factors, but face challenges as the number of factors increase. Consequently, integrating symbolic reasoning with language models, as implemented in AAM-CBR, is crucial for effectively handling cases involving many factors.
- Open Access
JBE-QA: Japanese Bar Exam QA Dataset for Assessing Legal Domain Knowledge
We introduce JBE-QA, a Japanese Bar Exam Question-Answering dataset to evaluate large language models' legal knowledge. Derived from the multiple-choice (tanto-shiki) section of the Japanese bar exam (2015-2024), JBE-QA provides the first comprehensive benchmark for Japanese legal-domain evaluation of LLMs. It covers the Civil Code, the Penal Code, and the Constitution, extending beyond the Civil Code focus of prior Japanese resources. Each question is decomposed into independent true/false judgments with structured contextual fields. The dataset contains 3,464 items with balanced labels. We evaluate 26 LLMs, including proprietary, open-weight, Japanese-specialised, and reasoning models. Our results show that proprietary models with reasoning enabled perform best, and the Constitution questions are generally easier than the Civil Code or the Penal Code questions.
Open AccessJBE-QA: Japanese Bar Exam QA Dataset for Assessing Legal Domain Knowledge
We introduce JBE-QA, a Japanese Bar Exam Question-Answering dataset to evaluate large language models' legal knowledge. Derived from the multiple-choice (tanto-shiki) section of the Japanese bar exam (2015-2024), JBE-QA provides the first comprehensive benchmark for Japanese legal-domain evaluation of LLMs. It covers the Civil Code, the Penal Code, and the Constitution, extending beyond the Civil Code focus of prior Japanese resources. Each question is decomposed into independent true/false judgments with structured contextual fields. The dataset contains 3,464 items with balanced labels. We evaluate 26 LLMs, including proprietary, open-weight, Japanese-specialised, and reasoning models. Our results show that proprietary models with reasoning enabled perform best, and the Constitution questions are generally easier than the Civil Code or the Penal Code questions.
- 1 October 2025
- Published by Springer Nature
- p. 403-415
Detection of Ransomware Attacks Using Federated Learning Based on the CNN Model
- 1 October 2025
- Published by Springer Nature
- p. 403-415
Detection of Ransomware Attacks Using Federated Learning Based on the CNN Model
- Open Access
NOWJ@COLIEE 2025: A Multi-stage Framework Integrating Embedding Models and Large Language Models for Legal Retrieval and Entailment
This paper presents the methodologies and results of the NOWJ team's participation across all five tasks at the COLIEE 2025 competition, emphasizing advancements in the Legal Case Entailment task (Task 2). Our comprehensive approach systematically integrates pre-ranking models (BM25, BERT, monoT5), embedding-based semantic representations (BGE-m3, LLM2Vec), and advanced Large Language Models (Qwen-2, QwQ-32B, DeepSeek-V3) for summarization, relevance scoring, and contextual re-ranking. Specifically, in Task 2, our two-stage retrieval system combined lexical-semantic filtering with contextualized LLM analysis, achieving first place with an F1 score of 0.3195. Additionally, in other tasks--including Legal Case Retrieval, Statute Law Retrieval, Legal Textual Entailment, and Legal Judgment Prediction--we demonstrated robust performance through carefully engineered ensembles and effective prompt-based reasoning strategies. Our findings highlight the potential of hybrid models integrating traditional IR techniques with contemporary generative models, providing a valuable reference for future advancements in legal information processing.
Open AccessNOWJ@COLIEE 2025: A Multi-stage Framework Integrating Embedding Models and Large Language Models for Legal Retrieval and Entailment
This paper presents the methodologies and results of the NOWJ team's participation across all five tasks at the COLIEE 2025 competition, emphasizing advancements in the Legal Case Entailment task (Task 2). Our comprehensive approach systematically integrates pre-ranking models (BM25, BERT, monoT5), embedding-based semantic representations (BGE-m3, LLM2Vec), and advanced Large Language Models (Qwen-2, QwQ-32B, DeepSeek-V3) for summarization, relevance scoring, and contextual re-ranking. Specifically, in Task 2, our two-stage retrieval system combined lexical-semantic filtering with contextualized LLM analysis, achieving first place with an F1 score of 0.3195. Additionally, in other tasks--including Legal Case Retrieval, Statute Law Retrieval, Legal Textual Entailment, and Legal Judgment Prediction--we demonstrated robust performance through carefully engineered ensembles and effective prompt-based reasoning strategies. Our findings highlight the potential of hybrid models integrating traditional IR techniques with contemporary generative models, providing a valuable reference for future advancements in legal information processing.
- 26 August 2025
- Published by Springer Nature in Applied Intelligence
- Vol. 55 (13) , 1-15
Uncovering connections: a reference network approach to statute law retrieval
- 26 August 2025
- Published by Springer Nature in Applied Intelligence
- Vol. 55 (13) , 1-15
Uncovering connections: a reference network approach to statute law retrieval
- Top Cited PapersOpen Access
- 30 July 2025
- Published by Elsevier in Computer Law & Security Review
- Vol. 58
LLMs for legal reasoning: A unified framework and future perspectives
- 30 July 2025
- Published by Elsevier in Computer Law & Security Review
- Vol. 58
Top Cited PapersOpen AccessLLMs for legal reasoning: A unified framework and future perspectives
- Open Access
VLQA: The First Comprehensive, Large, and High-Quality Vietnamese Dataset for Legal Question Answering
The advent of large language models (LLMs) has led to significant achievements in various domains, including legal text processing. Leveraging LLMs for legal tasks is a natural evolution and an increasingly compelling choice. However, their capabilities are often portrayed as greater than they truly are. Despite the progress, we are still far from the ultimate goal of fully automating legal tasks using artificial intelligence (AI) and natural language processing (NLP). Moreover, legal systems are deeply domain-specific and exhibit substantial variation across different countries and languages. The need for building legal text processing applications for different natural languages is, therefore, large and urgent. However, there is a big challenge for legal NLP in low-resource languages such as Vietnamese due to the scarcity of resources and annotated data. The need for labeled legal corpora for supervised training, validation, and supervised fine-tuning is critical. In this paper, we introduce the VLQA dataset, a comprehensive and high-quality resource tailored for the Vietnamese legal domain. We also conduct a comprehensive statistical analysis of the dataset and evaluate its effectiveness through experiments with state-of-the-art models on legal information retrieval and question-answering tasks.
Open AccessVLQA: The First Comprehensive, Large, and High-Quality Vietnamese Dataset for Legal Question Answering
The advent of large language models (LLMs) has led to significant achievements in various domains, including legal text processing. Leveraging LLMs for legal tasks is a natural evolution and an increasingly compelling choice. However, their capabilities are often portrayed as greater than they truly are. Despite the progress, we are still far from the ultimate goal of fully automating legal tasks using artificial intelligence (AI) and natural language processing (NLP). Moreover, legal systems are deeply domain-specific and exhibit substantial variation across different countries and languages. The need for building legal text processing applications for different natural languages is, therefore, large and urgent. However, there is a big challenge for legal NLP in low-resource languages such as Vietnamese due to the scarcity of resources and annotated data. The need for labeled legal corpora for supervised training, validation, and supervised fine-tuning is critical. In this paper, we introduce the VLQA dataset, a comprehensive and high-quality resource tailored for the Vietnamese legal domain. We also conduct a comprehensive statistical analysis of the dataset and evaluate its effectiveness through experiments with state-of-the-art models on legal information retrieval and question-answering tasks.