Papers by Trung Nguyen
Mutual-pairing Data Augmentation for Fewshot Continual Relation Extraction (2025.naacl-long)
Copied to clipboard
Nguyen Hoang Anh, Quyen Tran, Thanh Xuan Nguyen, Nguyen Thi Ngoc Diep, Linh Ngo Van, Thien Huu Nguyen, Trung Le
| Challenge: | Existing methods for Few-shot Continual Relation Extraction struggle with catastrophic forgetting and overfitting. |
| Approach: | They propose a method that transforms single input sentences into complex texts by integrating old and new data. |
| Outcome: | The proposed method sharpens model focus and improves model performance . it also uncovers fascinating behaviors of Sharpness-Aware Minimization (SAM) in Few-shot Continual Learning. |
LLM-XTM: Enhancing Cross-Lingual Topic Models with Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing cross-lingual topic models depend on sparse bilingual resources and often yield incoherent or weakly aligned topics. |
| Approach: | They propose a framework that integrates LLM-guided topic refinement with self-consistency uncertainty quantification to enable black-box, stable, and scalable enhancement of cross-lingual topic models. |
| Outcome: | Experiments on multilingual corpora show that the proposed framework achieves superior topic coherence and alignment while reducing reliance on bilingual dictionaries and expensive LLM calls. |
EMO: Embedding Model Distillation via Intra-Model Relation and Optimal Transport Alignments (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for knowledge distillation focus on direct output alignment, neglecting this crucial structural information. |
| Approach: | They propose a framework for knowledge distillation that maps tokens one-to-one and aligns attention matrix patterns using Centered Kernel Alignment. |
| Outcome: | The proposed framework significantly outperforms existing CTKD baselines. |
MTA: Multi-Granular Trajectory Alignment for Large Language Model Distillation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for reducing the computational cost of large language models (LLMs) focus on minimizing the divergence between the output probability distributions of the teacher and the student, which limits knowledge transfer. |
| Approach: | They propose a framework that aligns teacher and student representations along their layer-wise transformation trajectory. |
| Outcome: | The proposed framework outperforms state-of-the-art benchmarks on teacher–student layers. |
SRA: Span Representation Alignment for Large Language Model Distillation (2026.acl-long)
Copied to clipboard
Quoc Phong Dao, Hoang Son Nguyen, Pham Khanh Chi, Tung Nguyen, Linh Ngo Van, Nguyen Thi Ngoc Diep, Trung Le
| Challenge: | Existing approaches to cross-tokenizer knowledge distillation are brittle and sensitive to discrepancies between tokenizers. |
| Approach: | They propose a framework that shifts the unit of alignment from tokens to robust, tokenizer-agnostic spans and employ a geometric regularizer to preserve the structural integrity of the representation space. |
| Outcome: | The proposed framework outperforms state-of-the-art methods in cross-architecture distillation experiments. |
MIPIC: Matryoshka Representation Learning via Self-Distilled Intra-Relational and Progressive Information Chaining (2026.findings-acl)
Copied to clipboard
Phung Gia Huy, Hai An Vu, Minh-Phuc Truong, Thang Duc Tran, Linh Ngo Van, Thanh Hong Nguyen, Trung Le
| Challenge: | Existing approaches to train dense representations require explicit coordination of how information is arranged across embedding dimensionality and model depth. |
| Approach: | They propose a framework that trains Matryoshka representations using self-distilled intra-relational alignment and Progressive information chaining. |
| Outcome: | The proposed framework produces coherent and compact Matryoshka representations with significant performance advantages under low-dimensional models. |
Double Trouble: How to not Explain a Text Classifier’s Decisions Using Counterfactuals Synthesized by Masked Language Models? (2022.aacl-main)
Copied to clipboard
| Challenge: | Input Marginalization (IM) is a method that takes the prediction difference between before-and-after an input feature (here, a token) is removed as its attribution. |
| Approach: | They propose to use a BERT-based method to replace a token with a feature to give more plausible counterfactuals. |
| Outcome: | The proposed method is effective, but the Deletion-BERT metric is biased towards IM, and the results are not convincing. |
XTRA: Cross-Lingual Topic Modeling with Topic and Representation Alignments (2025.findings-emnlp)
Copied to clipboard
| Challenge: | XTRA aims to uncover shared semantic themes across languages . previous methods have achieved improvements in topic diversity but struggle to ensure high topic coherence and consistent alignment across languages. |
| Approach: | a new framework unifies Bag-of-Words modeling with multilingual embeddings is proposed to address this problem . XTRA introduces two core components: (1) representation alignment and (2) topic alignment to enforce cross-lingual consistency. |
| Outcome: | XTRA outperforms baselines in topic coherence, diversity, and alignment quality on multilingual corpora. |
PiC: A Phrase-in-Context Dataset for Phrase Understanding and Semantic Search (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing benchmarks for phrase-similarity compare phrases alone (without context) and phrases with context (with or without context). |
| Approach: | They propose to use a dataset of 28K noun phrases accompanied by their contextual Wikipedia pages to train machine phrase embeddings. |
| Outcome: | The proposed dataset improves ranking-models’ accuracy and pushes span selection models near human accuracy, which is 95% Exact Match (EM) on semantic search given a query phrase and a passage. |
Keyphrase Prediction from Video Transcripts: New Dataset and Directions (2022.coling-1)
Copied to clipboard
Amir Pouran Ben Veyseh, Quan Hung Tran, Seunghyun Yoon, Varun Manjunatha, Hanieh Deilamsalehy, Rajiv Jain, Trung Bui, Walter W. Chang, Franck Dernoncourt, Thien Huu Nguyen
| Challenge: | Existing studies on keyphrase prediction have focused on formal texts and informal-text domains. |
| Approach: | They propose to annotate large-scale video transcripts with keyphrases from live-stream video . they propose to feed models with paragraph-level keyphrase extraction to foster future research . |
| Outcome: | The proposed model improves keyphrase prediction in live-stream video transcripts by feeding models with paragraph-level keyphrases. |
Lizard: An Efficient Linearization Framework for Large Language Models (2026.acl-long)
Copied to clipboard
Chien Van Nguyen, Huy Huu Nguyen, Ruiyi Zhang, Hanieh Deilamsalehy, Puneet Mathur, Viet Dac Lai, Haoliang Wang, Jayakumar Subramanian, Ryan A. Rossi, Trung Bui, Nikos Vlassis, Franck Dernoncourt, Thien Huu Nguyen
| Challenge: | Existing linearization frameworks that rely on softmax attention with quadratic time and memory complexity pose significant computational and memory bottlenecks for long-context applications. |
| Approach: | They propose a linearization framework that transforms pretrained Transformer-based Large Language Models into subquadratic architectures that closely approximate softmax attention while preserving model quality. |
| Outcome: | Experiments show that the proposed framework outperforms existing methods by 9.4 - 24.5 points on the 5-shot MMLU benchmark and demonstrating superior associative recall. |
PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneck (2024.findings-naacl)
Copied to clipboard
| Challenge: | CLIP-based classifiers rely on the prompt containing a class name that is known to the text encoder and perform poorly on new classes or the classes whose names rarely appear on the Internet. |
| Approach: | They propose to use a set of text descriptors to express a class name into a textual descriptable and match the embeddings of the detected parts to their textual ones to compute a logit score. |
| Outcome: | The proposed classifier outperforms CLIP-based classifiers on zero-shot and supervised learning settings by 88.80% and 92.20% accuracy on CUB-200 and Stanford Dogs-120. |
Out of Order: How important is the sequential order of words in a sentence in Natural Language Understanding tasks? (2021.findings-acl)
Copied to clipboard
| Challenge: | In July 2019, RoBERTa was the first to surpass a human baseline on GLUE . since then, 13 more methods have outperformed humans on the GLu leaderboard . |
| Approach: | They found that 75% to 90% of correct predictions of BERT-based classifiers remain constant after input words are randomly shuffled. |
| Outcome: | The proposed model outperforms humans on GLUE and SQuAD 2.0. |
Beyond Coherence: Improving Temporal Consistency and Interpretability in Dynamic Topic Models (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing topic models capture bag-of-words statistics but lack semantic priors . interpretability remains shallow, relying on noisy top-word lists that obscure thematic clarity. |
| Approach: | They propose a variational framework to capture more faithful temporal trajectories . they propose to use entropy-regularized optimal transport to align entire topic constellations . |
| Outcome: | The proposed framework captures more faithful temporal trajectories and improves interpretability. |
Multi-Surrogate-Objective Optimization for Neural Topic Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Neural topic modeling incorporates multiple loss functions but can be difficult to optimize for disparate magnitudes of these losses. |
| Approach: | They propose a gradient-based multi-objective optimization approach that integrates MOO algorithms into the model without the need for hard-parameter sharing. |
| Outcome: | The proposed approach outperforms direct MOO applications on NTMs. |
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. |
Multi2Claim: Generating Scientific Claims from Multi-Choice Questions for Scientific Fact-Checking (2023.eacl-main)
Copied to clipboard
Neset Tan, Trung Nguyen, Josh Bensemann, Alex Peng, Qiming Bao, Yang Chen, Mark Gahegan, Michael Witbrock
| Challenge: | Existing scientific fact-checking datasets are limited due to expertise bottleneck . multi2Claim pipeline is a tool to convert multiple-choice questions into fact- checking data . |
| Approach: | They propose a pipeline for automatically converting multiple-choice questions into fact-checking data . they generate two large-scale datasets for scientific-fact-checker tasks . success at this task can help the reader understand scientific topics and promote science . |
| Outcome: | The proposed pipeline improves performance on two large-scale scientific fact-checking datasets. |
Causal Direct Preference Optimization for Language Model Alignment (2026.findings-eacl)
Copied to clipboard
| Challenge: | Empirical evaluations show that CDPO surpasses DPO-based baselines by achieving unbiased fine-tuning through causal reasoning. |
| Approach: | They propose a framework that incorporates causal inference principles to mitigate the influence of confounders and sharpen the signal of genuine human preferences. |
| Outcome: | The proposed framework preserves the tractability of direct optimization while enhancing robustness to spurious correlations and annotation biases. |
Preserving Generalization of Language models in Few-shot Continual Relation Extraction (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for Few-shot Continual Relations Extraction (FCRE) are limited in labeled training data and models must learn from a few new samples to solve new tasks. |
| Approach: | They propose a method that leverages often-discarded language model heads to integrate knowledge from new relations with limited labeled data while avoiding catastrophic forgetting. |
| Outcome: | The proposed method circumvents catastrophic forgetting and preserves prior knowledge from pre-trained backbones while maintaining accuracy of existing classifications. |
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. |
SlimLM: An Efficient Small Language Model for On-Device Document Assistance (2025.acl-demo)
Copied to clipboard
| Challenge: | Small language models (SLMs) show promise for mobile deployment, but their real world performance and applications on smartphones remain understudied. |
| Approach: | They propose a slim language model with a model size of 125M to 8B and a context length of 8B for efficient on-device processing. |
| Outcome: | The proposed model is based on a Samsung Galaxy S24 and shows comparable or superior performance. |
TALAS: Teacher-Anchored Layer Alignment with Adaptive Sharpness-Aware Minimization for Embedding Distillation (2026.acl-long)
Copied to clipboard
Quoc Phong Dao, Hoang Son Nguyen, Pham Khanh Chi, Linh Ngo Van, Nguyen Thi Ngoc Diep, Thien Huu Nguyen, Trung Le
| Challenge: | Existing methods that require a student to strictly mimic the teacher’s sentence embeddings or internal features often incur prohibitive computational costs and yield suboptimal performance due to the inherent capacity gap. |
| Approach: | They propose a Teacher-Anchored mechanism that selectively distills final sentence embeddings only into the student’s upper layers, thereby reducing overhead while respecting capacity constraints. |
| Outcome: | Empirical results show that TALAS outperforms existing methods while maintaining high performance. |
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. |
Unsupervised Domain Adaptation for Text Classification via Meta Self-Paced Learning (2022.coling-1)
Copied to clipboard
| Challenge: | Recent methods addressing unsupervised domain adaptation for textual tasks extracted domain-invariant representations through balancing between multiple objectives to align feature spaces between source and target domains. |
| Approach: | They propose to use meta-learning framework to train a neural network-based self-paced learning procedure in an end-to-end manner. |
| Outcome: | The proposed method significantly improves performance on target domains, surpassing state-of-the-art approaches. |
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. |