Ha-Thanh Nguyen
YOU?
Author Swipe
View article: Multi-Agent Legal Verifier Systems for Data Transfer Planning
Multi-Agent Legal Verifier Systems for Data Transfer Planning Open
Legal compliance in AI-driven data transfer planning is becoming increasingly critical under stringent privacy regulations such as the Japanese Act on the Protection of Personal Information (APPI). We propose a multi-agent legal verifier t…
View article: LLMs for legal reasoning: A unified framework and future perspectives
LLMs for legal reasoning: A unified framework and future perspectives Open
View article: Exploring GenAI Technologies within Collaborative Learning
Exploring GenAI Technologies within Collaborative Learning Open
View article: Enhancing Vietnamese VQA through Curriculum Learning on Raw and Augmented Text Representations
Enhancing Vietnamese VQA through Curriculum Learning on Raw and Augmented Text Representations Open
Visual Question Answering (VQA) is a multimodal task requiring reasoning across textual and visual inputs, which becomes particularly challenging in low-resource languages like Vietnamese due to linguistic variability and the lack of high-…
View article: On the Expressiveness of Visual Prompt Experts
On the Expressiveness of Visual Prompt Experts Open
Visual Prompt Tuning (VPT) has proven effective for parameter-efficient adaptation of pre-trained vision models to downstream tasks by inserting task-specific learnable prompt tokens. Despite its empirical success, a comprehensive theoreti…
View article: RAPID: Retrieval-Augmented Parallel Inference Drafting for Text-Based Video Event Retrieval
RAPID: Retrieval-Augmented Parallel Inference Drafting for Text-Based Video Event Retrieval Open
Retrieving events from videos using text queries has become increasingly challenging due to the rapid growth of multimedia content. Existing methods for text-based video event retrieval often focus heavily on object-level descriptions, ove…
View article: ConsRAG: Minimize LLM Hallucinations in the Legal Domain
ConsRAG: Minimize LLM Hallucinations in the Legal Domain Open
Retrieval-Augmented Generation (RAG) systems have shown potential in improving legal question-answering applications. However, they often struggle to provide precise information for legal queries, as broad-topic relevance may not always al…
View article: Exploiting LLMs' Reasoning Capability to Infer Implicit Concepts in Legal Information Retrieval
Exploiting LLMs' Reasoning Capability to Infer Implicit Concepts in Legal Information Retrieval Open
Statutory law retrieval is a typical problem in legal language processing, that has various practical applications in law engineering. Modern deep learning-based retrieval methods have achieved significant results for this problem. However…
View article: Graph-based and generative approaches to multi-document summarization
Graph-based and generative approaches to multi-document summarization Open
Multi-document summarization is a challenging problem in the Natural Language Processing field that has drawn a lot of interest from the research community. In this paper, we propose a two-phase pipeline to tackle the Vietnamese abstractiv…
View article: Drivers of Successful Adoption of Eco-innovation: Case Studies of Agricultural Cooperatives in Vietnam
Drivers of Successful Adoption of Eco-innovation: Case Studies of Agricultural Cooperatives in Vietnam Open
Research shows that external factors dominate the key determinants of eco-innovation (EI) adoption in organizations in the agriculture sector. Studies are needed to understand the link between internal organizational capabilities and EI ad…
View article: Detection of ransomware attacks using federated learning based on the CNN model
Detection of ransomware attacks using federated learning based on the CNN model Open
Computing is still under a significant threat from ransomware, which necessitates prompt action to prevent it. Ransomware attacks can have a negative impact on how smart grids, particularly digital substations. In addition to examining a r…
View article: GPTs and Language Barrier: A Cross-Lingual Legal QA Examination
GPTs and Language Barrier: A Cross-Lingual Legal QA Examination Open
In this paper, we explore the application of Generative Pre-trained Transformers (GPTs) in cross-lingual legal Question-Answering (QA) systems using the COLIEE Task 4 dataset. In the COLIEE Task 4, given a statement and a set of related le…
View article: Enhancing Legal Document Retrieval: A Multi-Phase Approach with Large Language Models
Enhancing Legal Document Retrieval: A Multi-Phase Approach with Large Language Models Open
Large language models with billions of parameters, such as GPT-3.5, GPT-4, and LLaMA, are increasingly prevalent. Numerous studies have explored effective prompting techniques to harness the power of these LLMs for various research problem…
View article: VLSP 2023 -- LTER: A Summary of the Challenge on Legal Textual Entailment Recognition
VLSP 2023 -- LTER: A Summary of the Challenge on Legal Textual Entailment Recognition Open
In this new era of rapid AI development, especially in language processing, the demand for AI in the legal domain is increasingly critical. In the context where research in other languages such as English, Japanese, and Chinese has been we…
View article: Balancing Exploration and Exploitation in LLM using Soft RLLF for Enhanced Negation Understanding
Balancing Exploration and Exploitation in LLM using Soft RLLF for Enhanced Negation Understanding Open
Finetuning approaches in NLP often focus on exploitation rather than exploration, which may lead to suboptimal models. Given the vast search space of natural language, this limited exploration can restrict their performance in complex, hig…
View article: A Deep Learning-Based System for Automatic Case Summarization
A Deep Learning-Based System for Automatic Case Summarization Open
This paper presents a deep learning-based system for efficient automatic case summarization. Leveraging state-of-the-art natural language processing techniques, the system offers both supervised and unsupervised methods to generate concise…
View article: Information Extraction from Lengthy Legal Contracts: Leveraging Query-Based Summarization and GPT-3.5
Information Extraction from Lengthy Legal Contracts: Leveraging Query-Based Summarization and GPT-3.5 Open
In the legal domain, extracting information from contracts poses significant challenges, primarily due to the scarcity of annotated data. In such situations, leveraging large language models (LLMs), such as the Generative Pretrained Transf…
View article: LawGiBa – Combining GPT, Knowledge Bases, and Logic Programming in a Legal Assistance System
LawGiBa – Combining GPT, Knowledge Bases, and Logic Programming in a Legal Assistance System Open
We present LawGiBa, a proof-of-concept demonstration system for legal assistance that combines GPT, legal knowledge bases, and Prolog’s logic programming structure to provide explanations for legal queries. This novel combination effective…
View article: LogiLaw Dataset Towards Reinforcement Learning from Logical Feedback (RLLF)
LogiLaw Dataset Towards Reinforcement Learning from Logical Feedback (RLLF) Open
Large Language Models (LLMs) face limitations in logical reasoning, which restrict their applicability in critical domains such as law. Current evaluation methods often lead to inaccurate assessments of LLMs’ capabilities due to their simp…
View article: Enhancing Logical Reasoning in Large Language Models to Facilitate Legal Applications
Enhancing Logical Reasoning in Large Language Models to Facilitate Legal Applications Open
Language serves as a vehicle for conveying thought, enabling communication among individuals. The ability to distinguish between diverse concepts, identify fairness and injustice, and comprehend a range of legal notions fundamentally relie…
View article: RMDM: A Multilabel Fakenews Dataset for Vietnamese Evidence Verification
RMDM: A Multilabel Fakenews Dataset for Vietnamese Evidence Verification Open
In this study, we present a novel and challenging multilabel Vietnamese dataset (RMDM) designed to assess the performance of large language models (LLMs), in verifying electronic information related to legal contexts, focusing on fake news…
View article: NOWJ1@ALQAC 2023: Enhancing Legal Task Performance with Classic Statistical Models and Pre-trained Language Models
NOWJ1@ALQAC 2023: Enhancing Legal Task Performance with Classic Statistical Models and Pre-trained Language Models Open
This paper describes the NOWJ1 Team's approach for the Automated Legal Question Answering Competition (ALQAC) 2023, which focuses on enhancing legal task performance by integrating classical statistical models and Pre-trained Language Mode…
View article: Constructing a Knowledge Graph for Vietnamese Legal Cases with Heterogeneous Graphs
Constructing a Knowledge Graph for Vietnamese Legal Cases with Heterogeneous Graphs Open
This paper presents a knowledge graph construction method for legal case documents and related laws, aiming to organize legal information efficiently and enhance various downstream tasks. Our approach consists of three main steps: data cra…
View article: NeCo@ALQAC 2023: Legal Domain Knowledge Acquisition for Low-Resource Languages through Data Enrichment
NeCo@ALQAC 2023: Legal Domain Knowledge Acquisition for Low-Resource Languages through Data Enrichment Open
In recent years, natural language processing has gained significant popularity in various sectors, including the legal domain. This paper presents NeCo Team's solutions to the Vietnamese text processing tasks provided in the Automated Lega…
View article: LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech
LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech Open
Self-supervised learning (SSL) is at the origin of unprecedented improvements in many different domains including computer vision and natural language processing. Speech processing drastically benefitted from SSL as most of the current dom…
View article: Black-Box Analysis: GPTs Across Time in Legal Textual Entailment Task
Black-Box Analysis: GPTs Across Time in Legal Textual Entailment Task Open
The evolution of Generative Pre-trained Transformer (GPT) models has led to significant advancements in various natural language processing applications, particularly in legal textual entailment. We present an analysis of GPT-3.5 (ChatGPT)…
View article: Semantic enrichment towards efficient speech representations
Semantic enrichment towards efficient speech representations Open
Over the past few years, self-supervised learned speech representations have emerged as fruitful replacements for conventional surface representations when solving Spoken Language Understanding (SLU) tasks. Simultaneously, multilingual mod…
View article: Synthesis of hybrid compounds of 24-nor-lupane triterpene and amino acids via C-28 amide linkage
Synthesis of hybrid compounds of 24-nor-lupane triterpene and amino acids via C-28 amide linkage Open
Betulinic acid derivatives exhibit different biological activity against diversified targets, such as anticarcinogenic activity in experimental animals, anti-HIV, antihyperglycemia, and anti-inflammatory in humans. In this work, we investi…
View article: Beyond Logic Programming for Legal Reasoning
Beyond Logic Programming for Legal Reasoning Open
Logic programming has long being advocated for legal reasoning, and several approaches have been put forward relying upon explicit representation of the law in logic programming terms. In this position paper we focus on the PROLEG logic-pr…
View article: A negation detection assessment of GPTs: analysis with the xNot360 dataset
A negation detection assessment of GPTs: analysis with the xNot360 dataset Open
Negation is a fundamental aspect of natural language, playing a critical role in communication and comprehension. Our study assesses the negation detection performance of Generative Pre-trained Transformer (GPT) models, specifically GPT-2,…