Search Results for author: Thuy-Trang Vu

Found 23 papers, 10 papers with code

CONGRAD:Conflicting Gradient Filtering for Multilingual Preference Alignment

no code implementations31 Mar 2025 Jiangnan Li, Thuy-Trang Vu, Christian Herold, Amirhossein Tebbifakhr, Shahram Khadivi, Gholamreza Haffari

To address this issue, we propose CONGRAD, a scalable and effective filtering method that selects high-quality preference samples with minimal gradient conflicts across languages.

SpeechDialogueFactory: Generating High-Quality Speech Dialogue Data to Accelerate Your Speech-LLM Development

1 code implementation31 Mar 2025 Minghan Wang, Ye Bai, Yuxia Wang, Thuy-Trang Vu, Ehsan Shareghi, Gholamreza Haffari

High-quality speech dialogue datasets are crucial for Speech-LLM development, yet existing acquisition methods face significant limitations.

Speech Synthesis Voice Cloning

Proverbs Run in Pairs: Evaluating Proverb Translation Capability of Large Language Model

no code implementations21 Jan 2025 Minghan Wang, Viet-Thanh Pham, Farhad Moghimifar, Thuy-Trang Vu

Despite achieving remarkable performance, machine translation (MT) research remains underexplored in terms of translating cultural elements in languages, such as idioms, proverbs, and colloquial expressions.

Language Modeling Language Modelling +4

The Best of Both Worlds: Bridging Quality and Diversity in Data Selection with Bipartite Graph

no code implementations16 Oct 2024 Minghao Wu, Thuy-Trang Vu, Lizhen Qu, Gholamreza Haffari

In this paper, we introduce GraphFilter, a novel method that represents the dataset as a bipartite graph, linking sentences to their constituent n-grams.

Computational Efficiency Diversity

SCAR: Efficient Instruction-Tuning for Large Language Models via Style Consistency-Aware Response Ranking

1 code implementation16 Jun 2024 Zhuang Li, Yuncheng Hua, Thuy-Trang Vu, Haolan Zhan, Lizhen Qu, Gholamreza Haffari

Recent studies emphasize that manually ensuring a consistent response style and maintaining high data quality in training sets can significantly improve the performance of fine-tuned Large Language Models (LLMs) while reducing the number of training examples needed.

Open-Ended Question Answering

Exploring the Potential of Multimodal LLM with Knowledge-Intensive Multimodal ASR

1 code implementation16 Jun 2024 Minghan Wang, Yuxia Wang, Thuy-Trang Vu, Ehsan Shareghi, Gholamreza Haffari

Recent advancements in multimodal large language models (MLLMs) have made significant progress in integrating information across various modalities, yet real-world applications in educational and scientific domains remain challenging.

Mixture-of-Skills: Learning to Optimize Data Usage for Fine-Tuning Large Language Models

no code implementations13 Jun 2024 Minghao Wu, Thuy-Trang Vu, Lizhen Qu, Gholamreza Haffari

In this work, we propose a general, model-agnostic, reinforcement learning framework, Mixture-of-Skills (MoS), that learns to optimize data usage automatically during the fine-tuning process.

Direct Evaluation of Chain-of-Thought in Multi-hop Reasoning with Knowledge Graphs

1 code implementation17 Feb 2024 Minh-Vuong Nguyen, Linhao Luo, Fatemeh Shiri, Dinh Phung, Yuan-Fang Li, Thuy-Trang Vu, Gholamreza Haffari

Large language models (LLMs) demonstrate strong reasoning abilities when prompted to generate chain-of-thought (CoT) explanations alongside answers.

Knowledge Graphs Multi-hop Question Answering +1

Continual Learning for Large Language Models: A Survey

no code implementations2 Feb 2024 Tongtong Wu, Linhao Luo, Yuan-Fang Li, Shirui Pan, Thuy-Trang Vu, Gholamreza Haffari

Large language models (LLMs) are not amenable to frequent re-training, due to high training costs arising from their massive scale.

Continual Learning Continual Pretraining +3

Adapting Large Language Models for Document-Level Machine Translation

no code implementations12 Jan 2024 Minghao Wu, Thuy-Trang Vu, Lizhen Qu, George Foster, Gholamreza Haffari

We provide an in-depth analysis of these LLMs tailored for DocMT, examining translation errors, discourse phenomena, strategies for training and inference, the data efficiency of parallel documents, recent test set evaluations, and zero-shot crosslingual transfer.

Document Level Machine Translation Domain Generalization +2

Active Continual Learning: On Balancing Knowledge Retention and Learnability

no code implementations6 May 2023 Thuy-Trang Vu, Shahram Khadivi, Mahsa Ghorbanali, Dinh Phung, Gholamreza Haffari

Acquiring new knowledge without forgetting what has been learned in a sequence of tasks is the central focus of continual learning (CL).

Active Learning Continual Learning +1

Koala: An Index for Quantifying Overlaps with Pre-training Corpora

no code implementations26 Mar 2023 Thuy-Trang Vu, Xuanli He, Gholamreza Haffari, Ehsan Shareghi

In very recent years more attention has been placed on probing the role of pre-training data in Large Language Models (LLMs) downstream behaviour.

Memorization

Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data Selection

1 code implementation EMNLP 2021 Thuy-Trang Vu, Xuanli He, Dinh Phung, Gholamreza Haffari

Once the in-domain data is detected by the classifier, the NMT model is then adapted to the new domain by jointly learning translation and domain discrimination tasks.

Contrastive Learning Machine Translation +3

Effective Unsupervised Domain Adaptation with Adversarially Trained Language Models

1 code implementation EMNLP 2020 Thuy-Trang Vu, Dinh Phung, Gholamreza Haffari

Recent work has shown the importance of adaptation of broad-coverage contextualised embedding models on the domain of the target task of interest.

named-entity-recognition Named Entity Recognition +2

Learning How to Active Learn by Dreaming

1 code implementation ACL 2019 Thuy-Trang Vu, Ming Liu, Dinh Phung, Gholamreza Haffari

Heuristic-based active learning (AL) methods are limited when the data distribution of the underlying learning problems vary.

Active Learning named-entity-recognition +6

Automatic Post-Editing of Machine Translation: A Neural Programmer-Interpreter Approach

1 code implementation EMNLP 2018 Thuy-Trang Vu, Gholamreza Haffari

Automated Post-Editing (PE) is the task of automatically correct common and repetitive errors found in machine translation (MT) output.

Automatic Post-Editing Translation

Cannot find the paper you are looking for? You can Submit a new open access paper.