Papers by Hoang Nguyen
FAID: Fine-grained AI-generated Text Detection using Multi-task Auxiliary and Multi-level Contrastive Learning (2026.eacl-long)
Copied to clipboard
Minh Ngoc Ta, Dong Cao Van, Duc-Anh Hoang, Minh Le-Anh, Truong Nguyen, My Anh Tran Nguyen, Yuxia Wang, Preslav Nakov, Dinh Viet Sang
| Challenge: | Existing binary detection frameworks for human-written, LLM-generated and human-LLM collaborative texts are challenging . a recent study focused on binary detection, i.e., human vs. LLM, or on fine-grained detection limited to English. |
| Approach: | They propose a fine-grained detection framework to classify text into three categories . they use multilingual datasets and a multi-domain, multi-generator dataset . |
| Outcome: | The proposed framework outperforms baselines on unseen domains and new LLMs. |
RecGPT: Generative Pre-training for Text-based Recommendation (2024.acl-short)
Copied to clipboard
| Challenge: | Existing models for text-based recommendation lack data sparsity and flexibility to capture fluctuations in user preferences over time. |
| Approach: | They present the first domain-adapted and fully-trained large language model for text-based recommendation. |
| Outcome: | The proposed model outperforms baseline models on rating prediction and sequential recommendation tasks. |
Stronger, Lighter, Better: Towards Life-Long Attribute Value Extraction for E-Commerce Products (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing models for attribute value extraction struggle for parameter efficiency and reliability due to data contamination and catastrophic forgetting. |
| Approach: | They propose to decouple product type and attribute to promote de-contamination and parameter efficiency while scaling up. |
| Outcome: | The proposed model achieves state-of-the-art performance with affordable parameter size, least historical knowledge forgetting, and greatest robustness against noises. |
PhoMT: A High-Quality and Large-Scale Benchmark Dataset for Vietnamese-English Machine Translation (2021.emnlp-main)
Copied to clipboard
| Challenge: | We present a high-quality and large-scale Vietnamese-English parallel dataset . our dataset is 2.9M pairs larger than the benchmark Vietnamese- English corpus . |
| Approach: | They present a large-scale Vietnamese-English parallel dataset with 3.02M sentence pairs . they compare strong neural baselines and well-known automatic translation engines . |
| Outcome: | The proposed dataset is 2.9M pairs larger than the benchmark Vietnamese-English corpus IWSLT15. |
Enhancing Cross-lingual Transfer via Phonemic Transcription Integration (2023.findings-acl)
Copied to clipboard
| Challenge: | Previous cross-lingual transfer methods are limited to orthographic representation learning via textual scripts. |
| Approach: | They propose a phonemic transcription framework that incorporates phonemic translations as an additional linguistic modality beyond the orthographic transcriptions for cross-lingual transfer. |
| Outcome: | The proposed framework captures local one-to-one alignment between two different modalities and integrates bilingual dictionaries into multilingual contexts. |
VLUE: A New Benchmark and Multi-task Knowledge Transfer Learning for Vietnamese Natural Language Understanding (2024.findings-naacl)
Copied to clipboard
| Challenge: | a lack of standard evaluation metrics and benchmarks makes it difficult to identify strengths of Vietnamese NLP models. |
| Approach: | They propose to establish a standardized set of benchmarks for Vietnamese NLU . they propose to evaluate Vietnamese language understanding models using a pre-trained model . |
| Outcome: | The proposed model combines proficiency of a multilingual pre-trained model with Vietnamese linguistic knowledge. |
SpecMind: Cognitively Inspired, Interactive Multi-Turn Framework for Postcondition Inference (2026.acl-long)
Copied to clipboard
Cuong Chi Le, Minh V.t. Pham, Tung D. Vu, Van Duc Cuong, Phan Nhat Huy, Phan Nhat Hoang, Tien N. Nguyen
| Challenge: | Existing methods for generating specifications are limited and often fail to infer semantic specifications such as pre-/postconditions. |
| Approach: | They propose a framework that treats LLMs as exploratory reasoners rather than one-shot generators. |
| Outcome: | The proposed framework outperforms state-of-the-art methods in accuracy and completeness of generated postconditions. |
VisualCoder: Guiding Large Language Models in Code Execution with Fine-grained Multimodal Chain-of-Thought Reasoning (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing approaches to enhance large language models' ability to predict program behavior struggle with dynamic reasoning tasks. |
| Approach: | They propose a visual control flow graph that integrates CoT reasoning with a control flow . they aim to improve performance in program behavior prediction, error detection and output generation . |
| Outcome: | The proposed approach improves program behavior prediction, error detection, and output generation. |
ClaimPKG: Enhancing Claim Verification via Pseudo-Subgraph Generation with Lightweight Specialized LLM (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing verification methods rely on unstructured text corpora to break down claims . despite strong reasoning abilities, modern LLMs struggle with modular pipelines . |
| Approach: | They propose a framework that integrates knowledge graphs with LLM reasoning . they propose KGs provide structured, semantically rich representations . |
| Outcome: | The proposed framework outperforms baselines on the FactKG dataset by 9%-12% accuracy points across multiple categories. |
Verify-in-the-Graph: Entity Disambiguation Enhancement for Complex Claim Verification with Interactive Graph Representation (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing approaches to claim verification are based on decomposing claims into sub-claims and querying a knowledge base to resolve hidden or ambiguous entities. |
| Approach: | They propose a framework that leverages the reasoning and comprehension abilities of LLM agents to solve ambiguous entities in a graph. |
| Outcome: | The proposed framework achieves competitive performance compared to baselines across benchmarks. |
ViHOS: Hate Speech Spans Detection for Vietnamese (2023.eacl-main)
Copied to clipboard
| Challenge: | Increasing use of social networking sites can cause problems for human moderators to review tagged comments. |
| Approach: | They present a dataset that contains 26k spans on 11k comments and detailed annotation guidelines . they also provide definitions of hateful and offensive spans in Vietnamese comments . |
| Outcome: | The proposed dataset shows that it is difficult to detect specific types of spans in the dataset . the dataset is the first human-annotated corpus containing 26k spans on 11k comments . |
Automated Generation of Accurate & Fluent Medical X-ray Reports (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing medical report generation efforts focus on producing human-readable reports, yet the generated text may not be well aligned to the clinical facts. |
| Approach: | They propose to automate the generation of medical reports from chest X-ray image inputs . medical reports are the primary medium, which physicians communicate findings from scans - authors say . |
| Outcome: | The proposed method achieves fluency and clinical accuracy on common metrics. |
Meeting Decision Tracker: Making Meeting Minutes with De-Contextualized Utterances (2022.aacl-demo)
Copied to clipboard
| Challenge: | Existing systems to itemize meetings' decisions are lacking in their raw form due to utterance collapse. |
| Approach: | They propose a prototype system to construct decision items that deal with utterance collapse in natural conversation. |
| Outcome: | The proposed system improves the user experience by dealing with utterance collapse in natural conversation. |
Fooling the Textual Fooler via Randomizing Latent Representations (2024.findings-acl)
Copied to clipboard
| Challenge: | Several adversarial attacks can compromise the model without accessing the model architecture or model parameters (i.e., a blackbox setting) Several studies have revealed that deep NLP models are vulnerable to adversarials that slightly perturb the input to cause the models to misbehave. |
| Approach: | They propose a lightweight and attack-agnostic defense that perplexes the process of generating an adversarial example in query-based black-box attacks. |
| Outcome: | The proposed defense is lightweight and attack-agnostic and does not necessitate additional computational overhead during training nor does it rely on assumptions about the potential adversarial perturbation set while having a negligible impact on the model’s accuracy. |
CORI: CJKV Benchmark with Romanization Integration - a Step towards Cross-lingual Transfer beyond Textual Scripts (2024.lrec-main)
Copied to clipboard
| Challenge: | Naively assuming English as a source language may hinder cross-lingual transfer . despite recent advances in cross-linguistic research, most studies have restricted themselves to two major assumptions . |
| Approach: | They propose to integrate Romanized transcription beyond textual scripts to capture contact between these languages . they propose to use a benchmark dataset to further encourage in-depth studies of language contact . |
| Outcome: | The proposed method allows for enhanced cross-lingual representations and effective zero-shot cross-linguistic transfer. |
VN-MTEB: Vietnamese Massive Text Embedding Benchmark (2026.findings-eacl)
Copied to clipboard
| Challenge: | a lack of large-scale test datasets makes it difficult to evaluate AI models before deploying them in real-world projects. |
| Approach: | They propose a Vietnamese benchmark for embedding models that leverages large language models and embeddable models to translate and filter samples from the Massive Multilingual Text Embedding Benchmark. |
| Outcome: | The proposed benchmark outperforms existing models in Vietnamese and English tasks with 41 datasets. |
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
| 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. |
Who’s Who: Large Language Models Meet Knowledge Conflicts in Practice (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent large-scale pretrained language models excel in tasks requiring natural language understanding, but they often "hallucinate" plausible but incorrect content due to outdated or incorrect pretraining information. |
| Approach: | They propose a public benchmark dataset to examine model’s behavior in knowledge conflict situations. |
| Outcome: | The proposed model induces conflicts by asking about a common property among entities having the same name, resulting in questions with up to 8 distinctive answers. |
A Self-enhancement Multitask Framework for Unsupervised Aspect Category Detection (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent work has focused on learning embedding spaces for seed words and sentences to establish similarities between sentences and aspects. |
| Approach: | They propose a framework that enhances the quality of initial seed words and selects high-quality sentences instead of using the entire dataset. |
| Outcome: | The proposed framework surpasses strong baselines on standard datasets and improves on the noise resolution task. |
SemViQA: A Semantic Question Answering System for Vietnamese Information Fact-Checking (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing methods struggle with semantic ambiguity, homonyms, and complex linguistic structures, often trading accuracy for efficiency. |
| Approach: | They propose a Vietnamese fact-checking framework that integrates SER and TVC to achieve 78.97% strict accuracy. |
| Outcome: | The proposed framework achieves state-of-the-art accuracy with 78.97% strict accuracy on ISE-DSC01 and 80.82% on ViWikiFC while maintaining competitive accuracy. |
Dynamic Semantic Matching and Aggregation Network for Few-shot Intent Detection (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies show that multi-level matching is difficult due to the scarcity of available annotated utterances. |
| Approach: | They propose a method where semantic components are distilled from utterances via multi-head self-attention with additional dynamic regularization constraints. |
| Outcome: | The proposed method improves representations of labeled and unlabeled instances while retaining high-level information. |
Mastering the Craft of Data Synthesis for CodeLLMs (2025.naacl-long)
Copied to clipboard
Meng Chen, Philip Arthur, Qianyu Feng, Cong Duy Vu Hoang, Yu-Heng Hong, Mahdi Kazemi Moghaddam, Omid Nezami, Duc Thien Nguyen, Gioacchino Tangari, Duy Vu, Thanh Vu, Mark Johnson, Krishnaram Kenthapadi, Don Dharmasiri, Long Duong, Yuan-Fang Li
| Challenge: | Large language models (LLMs) have shown impressive performance in code understanding and generation. |
| Approach: | They propose a systematic review of large language models and their taxonomy and propose specialized LLMs for code-related tasks. |
| Outcome: | The proposed models have shown to be highly effective in coding tasks. |
ViHealthBERT: Pre-trained Language Models for Vietnamese in Health Text Mining (2022.lrec-1)
Copied to clipboard
| Challenge: | Recent large-scale language models show remarkable achievements in key NLP tasks such as Question Answering and Text Summarization. |
| Approach: | They propose a domain-specific pre-trained Vietnamese language model that outperforms the general domain language models. |
| Outcome: | The proposed model outperforms the general domain language models in Vietnamese datasets while outperforming the general-domain language models. |
Layer-Wise High-Impact Parameter Ratio Optimization in Post-Training Quantization for Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods to quantize large language models suffer from significant accuracy loss at low bit-widths due to high-impact parameters. |
| Approach: | They propose a quadratic optimization framework that quantizes high-impact parameters to moderate bit-widths while quantizing low bit-wideths. |
| Outcome: | The proposed framework preserves high-impact parameters while preserving memory usage. |
CoF-CoT: Enhancing Large Language Models with Coarse-to-Fine Chain-of-Thought Prompting for Multi-domain NLU Tasks (2023.emnlp-main)
Copied to clipboard
| Challenge: | Chain-of-Thought prompting is popular in reasoning tasks, but its application to Large Language Models (LLMs) in Natural Language Understanding (NLU) is under-explored. |
| Approach: | They propose a Coarse-to-Fine Chain-of-Thought approach that breaks down NLU tasks into multiple reasoning steps where LLMs can learn to acquire essential concepts. |
| Outcome: | The proposed approach is effective in assisting the LLMs adapt to multi-grained NLU tasks under zero-shot and few-shot multi-domain settings. |