Papers by Hieu Nguyen

20 papers
ULLME: A Unified Framework for Large Language Model Embeddings with Generation-Augmented Learning (2024.emnlp-demo)

Copied to clipboard

Challenge: Existing frameworks for large language model embeddings have limited support for only a limited range of architectures and fine-tuning strategies.
Approach: They propose a framework that enables bidirectional attention across various LLMs and supports a range of fine-tuning strategies.
Outcome: The proposed framework enables bidirectional attention across various LLMs and supports a range of fine-tuning strategies.
Hierarchical Selection of Important Context for Generative Event Causality Identification with Optimal Transports (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for Event Causality Identification (ECI) rely on external toolkits or human annotation to obtain training signals.
Approach: They propose a generative framework that leverages Optimal Transport to automatically select the most important sentences and words from full documents.
Outcome: The proposed framework can predict causal relation between two events in text without external tools.
Improving Vietnamese-English Cross-Lingual Retrieval for Legal and General Domains (2025.naacl-short)

Copied to clipboard

Challenge: Existing document retrieval systems focus on a single language, targeting resource-rich languages like English or Chinese.
Approach: They propose auxiliary loss function and symmetrical training strategy for cross-lingual retrieval between Vietnamese and English . they propose a dataset that covers the general domain and extends to the legal field .
Outcome: The proposed dataset significantly improves state-of-the-art models on cross-lingual retrieval tasks.
Multilingual SubEvent Relation Extraction: A Novel Dataset and Structure Induction Method (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for subevent relation extraction (SRE) focus on sequential order of words in texts to enhance representation learning.
Approach: They propose a method that learns to induce effective graph structures for input texts . they use word alignment frameworks with dependency paths and optimal transport .
Outcome: The proposed method is able to induce effective graph structures for input texts to boost representation learning.
The Dots Have Their Values: Exploiting the Node-Edge Connections in Graph-based Neural Models for Document-level Relation Extraction (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for document-level relation extraction do not capture the representations of the nodes in the graphs.
Approach: They propose to explicitly compute the representations for the nodes in the graph-based edge-oriented model for Document-level Relation Extraction (DRE) . they propose to introduce two novel representation regularization mechanisms to improve the representation vectors for DRE.
Outcome: The proposed model achieves state-of-the-art performance on two benchmark datasets.
Event Causality Identification via Generation of Important Context Words (2022.starsem-1)

Copied to clipboard

Challenge: Prior work focused on identifying causal relation between two event mentions . current models do not output important contexts for causal prediction of two mentions.
Approach: They propose to use dependency path generation as a complementary task for ECI.
Outcome: The proposed model can generate both causal relation and dependency path words from input sentences.
VietMix: A Naturally-Occurring Parallel Corpus and Augmentation Framework for Vietnamese-English Code-Mixed Machine Translation (2026.eacl-long)

Copied to clipboard

Challenge: Existing approaches to machine translation (MT) systems degrade when faced with code-mixed text.
Approach: They propose a system that can augment Vietnamese-English code-mixed text with iterative fine-tuning and targeted filtering.
Outcome: The proposed framework outperforms strong back-translation baselines and improves zero-shot models by up to +11.9 points.
OZSpeech: One-step Zero-shot Speech Synthesis with Learned-Prior-Conditioned Flow Matching (2025.acl-long)

Copied to clipboard

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.
Contextualized Soft Prompts for Extraction of Event Arguments (2023.findings-acl)

Copied to clipboard

Challenge: Existing prompt-based methods for event argument extraction rely on discrete and manually-designed prompts that cannot exploit specific context for each example.
Approach: They propose a prompt-based method that introduces soft prompts to facilitate encoding of individual example context and multiple relevant documents to boost EAE.
Outcome: The proposed method extensively evaluates on benchmark datasets to demonstrate its benefits with state-of-the-art performance.
CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages (2024.lrec-main)

Copied to clipboard

Challenge: Existing training datasets for large language models are often not fully disclosed.
Approach: They propose a multilingual dataset with 6.3 trillion tokens in 167 languages . they use a pipeline of multiple stages to achieve the best quality for model training .
Outcome: The proposed dataset is cleaned and deduplicated to achieve the best quality for model training . lack of transparency has hindered research on attributing and addressing hallucination and bias issues . 6.3 trillion tokens in 167 languages are used to train multilingual LLMs .
ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning (2023.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in natural language processing (NLP) have led to significant breakthroughs in the field.
Approach: They evaluate ChatGPT over multiple tasks with diverse languages and large datasets to provide more comprehensive information for multilingual NLP applications.
Outcome: The proposed model can process and generate texts for multiple languages due to its multilingual training data.
Exploiting Document Structures and Cluster Consistencies for Event Coreference Resolution (2021.acl-long)

Copied to clipboard

Challenge: Existing deep learning models for event coreference resolution are limited in that they cannot exploit important interactions between relevant objects for ECR.
Approach: They propose a deep learning model that groups coreferent event mentions into the same clusters . they use document structures to capture relevant objects for ECR .
Outcome: The proposed model achieves state-of-the-art on two benchmark datasets.
ViT5: Pretrained Text-to-Text Transformer for Vietnamese Language Generation (2022.naacl-srw)

Copied to clipboard

Challenge: Existing models for the English language have been used to train on large corpus of high-quality texts.
Approach: They present a pretrained Transformer-based encoder-decoder model for the Vietnamese language . they benchmark ViT5 on two downstream text generation tasks .
Outcome: The proposed model outperforms existing models on Vietnamese Abstractive Summarization and Named Entity Recognition tasks.
Class based Influence Functions for Error Detection (2023.acl-short)

Copied to clipboard

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.
LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs (2025.naacl-long)

Copied to clipboard

Challenge: Using format-following capabilities, state-of-the-art large language models (LLMs) can be leveraged to tailor outputs to specific task formats.
Approach: They propose to define a format bias evaluation metric and establish effective strategies to reduce it.
Outcome: The proposed evaluation reduces the variance in ChatGPT’s performance among wrapping formats from 235.33 to 0.71 (%2)
Explainable Disentangled Representation Learning for Generalizable Authorship Attribution in the Era of Generative AI (2026.acl-long)

Copied to clipboard

Challenge: Existing methods struggle with content-style entanglement, leading to poor generalization across domains.
Approach: They propose an explanation-by-design framework that explicitly disentangles style from content through architectural separation-by design.
Outcome: The proposed framework disentangles style from content through architectural separation-by-design.
“Global is Good, Local is Bad?”: Understanding Brand Bias in LLMs (2024.emnlp-main)

Copied to clipboard

Challenge: a recent study examined social biases in LLMs but brand bias has received little attention.
Approach: They examine the behavior of LLMs in the market place by analyzing a brand-based dataset . they find a consistent pattern of brand bias in this space .
Outcome: The proposed model favors established global brands while marginalizing local ones . the proposed model could boost local brand preference in LLM outputs in specific contexts .
Introducing a New Dataset for Event Detection in Cybersecurity Texts (2020.emnlp-main)

Copied to clipboard

Challenge: a large amount of text data is produced to report and discuss cyber vulnerabilities . detecting cybersecurity events is necessary to keep us informed about the fast growing number of such events reported in text.
Approach: They propose a dataset characterizing the manual annotation for 30 important cybersecurity event types and a large dataset to develop deep learning models.
Outcome: The proposed dataset characterizes the manual annotation for 30 important event types and supports the modeling of document-level information to improve the performance.
MaGiX: A Multi-Granular Adaptive Graph Intelligence Framework for Enhancing Cross-Lingual RAG (2025.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in Graph-based RAG (GRAG) frameworks focus on knowledge graphs for cross-lingual retrieval.
Approach: They propose a new GRAG framework for cross-lingual question answering . MaGiX constructs a multi-granular cross-linguistic knowledge graph using fine-grained attribute descriptions and cross-synonym edges.
Outcome: The proposed framework outperforms prior GRAG systems in retrieval accuracy and generation quality.
HiGraAgent: Dual-Agent Adaptive Reasoning over Hierarchical Knowledge Graph for Open Domain Multi-hop Question Answering (2026.findings-eacl)

Copied to clipboard

Challenge: Existing approaches to multi-hop question answering lack a robust and flexible approach to QA . prior work showed compositionality gap persists even for Large Language Models .
Approach: They propose a framework that unifies graph-based retrieval with adaptive reasoning . HiGraAgent uses a hierarchical knowledge Graph with entity alignment .
Outcome: The proposed framework outperforms the strongest graph-based method on hotpotQA, 2WikiMultihopQA, and MuSiQue.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations