Search Results for author: Xiaobao Wu

Found 44 papers, 30 papers with code

Detecting Harmful Memes with Decoupled Understanding and Guided CoT Reasoning

1 code implementation10 Jun 2025 Fengjun Pan, Anh Tuan Luu, Xiaobao Wu

Building on these textual descriptions, we further incorporate targeted, interpretable human-crafted guidelines to guide models' reasoning under zero-shot CoT prompting.

Meme Classification

SCOPE: Compress Mathematical Reasoning Steps for Efficient Automated Process Annotation

1 code implementation20 May 2025 Huimin Xu, Xin Mao, Feng-Lin Li, Xiaobao Wu, Wang Chen, Wei zhang, Anh Tuan Luu

Process Reward Models (PRMs) have demonstrated promising results in mathematical reasoning, but existing process annotation approaches, whether through human annotations or Monte Carlo simulations, remain computationally expensive.

Mathematical Reasoning

Aspect-Based Summarization with Self-Aspect Retrieval Enhanced Generation

no code implementations17 Apr 2025 Yichao Feng, Shuai Zhao, Yueqiu Li, Luwei Xiao, Xiaobao Wu, Anh Tuan Luu

To address these challenges, in this paper, we propose a novel framework for aspect-based summarization: Self-Aspect Retrieval Enhanced Summary Generation.

Hallucination In-Context Learning +2

HyperGraphRAG: Retrieval-Augmented Generation with Hypergraph-Structured Knowledge Representation

1 code implementation27 Mar 2025 Haoran Luo, Haihong E, Guanting Chen, Yandan Zheng, Xiaobao Wu, Yikai Guo, Qika Lin, Yu Feng, Zemin Kuang, Meina Song, Yifan Zhu, Luu Anh Tuan

To retrieve and generate over hypergraphs, we introduce a complete pipeline with a hypergraph construction method, a hypergraph retrieval strategy, and a hypergraph-guided generation mechanism.

RAG Retrieval +1

CutPaste&Find: Efficient Multimodal Hallucination Detector with Visual-aid Knowledge Base

no code implementations18 Feb 2025 Cong-Duy Nguyen, Xiaobao Wu, Duc Anh Vu, Shuai Zhao, Thong Nguyen, Anh Tuan Luu

Large Vision-Language Models (LVLMs) have demonstrated impressive multimodal reasoning capabilities, but they remain susceptible to hallucination, particularly object hallucination where non-existent objects or incorrect attributes are fabricated in generated descriptions.

Attribute Hallucination +2

Hierarchical Graph Topic Modeling with Topic Tree-based Transformer

no code implementations17 Feb 2025 Delvin Ce Zhang, Menglin Yang, Xiaobao Wu, Jiasheng Zhang, Hady W. Lauw

We thus propose a Hierarchical Graph Topic Modeling Transformer to integrate both topic hierarchy within documents and graph hierarchy across documents into a unified Transformer.

Specificity Topic Models

KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search

1 code implementation31 Jan 2025 Haoran Luo, Haihong E, Yikai Guo, Qika Lin, Xiaobao Wu, Xinyu Mu, Wenhao Liu, Meina Song, Yifan Zhu, Luu Anh Tuan

Moreover, it employs MCTS, a heuristic search method driven by policy and reward models, to balance agentic exploration's performance and search space.

Heuristic Search Knowledge Base Question Answering

RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios

1 code implementation12 Dec 2024 Ruiwen Zhou, Wenyue Hua, Liangming Pan, Sitao Cheng, Xiaobao Wu, En Yu, William Yang Wang

This paper introduces RuleArena, a novel and challenging benchmark designed to evaluate the ability of large language models (LLMs) to follow complex, real-world rules in reasoning.

Logical Reasoning Long-Context Understanding

Motion-aware Contrastive Learning for Temporal Panoptic Scene Graph Generation

no code implementations10 Dec 2024 Thong Thanh Nguyen, Xiaobao Wu, Yi Bin, Cong-Duy T Nguyen, See-Kiong Ng, Anh Tuan Luu

To overcome this limitation, we introduce a contrastive representation learning framework that focuses on motion pattern for temporal scene graph generation.

Contrastive Learning Graph Generation +3

Curriculum Demonstration Selection for In-Context Learning

no code implementations27 Nov 2024 Duc Anh Vu, Nguyen Tran Cong Duy, Xiaobao Wu, Hoang Minh Nhat, Du Mingzhe, Nguyen Thanh Thong, Anh Tuan Luu

Large Language Models (LLMs) have shown strong in-context learning (ICL) abilities with a few demonstrations.

In-Context Learning

Are LLMs Good Zero-Shot Fallacy Classifiers?

1 code implementation19 Oct 2024 Fengjun Pan, Xiaobao Wu, Zongrui Li, Anh Tuan Luu

To elicit fallacy-related knowledge and reasoning abilities of LLMs, we propose diverse single-round and multi-round prompting schemes, applying different task-specific instructions such as extraction, summarization, and Chain-of-Thought reasoning.

Misinformation

COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement

1 code implementation12 Oct 2024 Yuxi Xie, Anirudh Goyal, Xiaobao Wu, Xunjian Yin, Xiao Xu, Min-Yen Kan, Liangming Pan, William Yang Wang

Our approach models multiple token dependencies within manageable context windows, enabling the model to perform iterative refinement internally during the generation process.

Code Generation Computational Efficiency +3

Weak-to-Strong Backdoor Attack for Large Language Models

no code implementations26 Sep 2024 Shuai Zhao, Leilei Gan, Zhongliang Guo, Xiaobao Wu, Luwei Xiao, Xiaoyu Xu, Cong-Duy Nguyen, Luu Anh Tuan

Despite being widely applied due to their exceptional capabilities, Large Language Models (LLMs) have been proven to be vulnerable to backdoor attacks.

Backdoor Attack Knowledge Distillation +1

MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning

1 code implementation4 Jul 2024 Thong Nguyen, Yi Bin, Xiaobao Wu, Xinshuai Dong, Zhiyuan Hu, Khoi Le, Cong-Duy Nguyen, See-Kiong Ng, Luu Anh Tuan

To address these problems, we propose MAMA, a new approach to learning video-language representations by utilizing a contrastive objective with a subtractive angular margin to regularize cross-modal representations in their effort to reach perfect similarity.

Language Modeling Language Modelling +4

A Survey of Recent Backdoor Attacks and Defenses in Large Language Models

no code implementations10 Jun 2024 Shuai Zhao, Meihuizi Jia, Zhongliang Guo, Leilei Gan, Xiaoyu Xu, Xiaobao Wu, Jie Fu, Yichao Feng, Fengjun Pan, Luu Anh Tuan

Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings.

parameter-efficient fine-tuning

Modeling Dynamic Topics in Chain-Free Fashion by Evolution-Tracking Contrastive Learning and Unassociated Word Exclusion

2 code implementations28 May 2024 Xiaobao Wu, Xinshuai Dong, Liangming Pan, Thong Nguyen, Anh Tuan Luu

However, existing models suffer from repetitive topic and unassociated topic issues, failing to reveal the evolution and hindering further applications.

Contrastive Learning Diversity +2

AKEW: Assessing Knowledge Editing in the Wild

1 code implementation29 Feb 2024 Xiaobao Wu, Liangming Pan, William Yang Wang, Anh Tuan Luu

Knowledge editing injects knowledge updates into language models to keep them correct and up-to-date.

Articles counterfactual +2

Topic Modeling as Multi-Objective Contrastive Optimization

no code implementations12 Feb 2024 Thong Nguyen, Xiaobao Wu, Xinshuai Dong, Cong-Duy T Nguyen, See-Kiong Ng, Anh Tuan Luu

Secondly, we explicitly cast contrastive topic modeling as a gradient-based multi-objective optimization problem, with the goal of achieving a Pareto stationary solution that balances the trade-off between the ELBO and the contrastive objective.

Contrastive Learning Diversity +2

A Survey on Neural Topic Models: Methods, Applications, and Challenges

2 code implementations27 Jan 2024 Xiaobao Wu, Thong Nguyen, Anh Tuan Luu

In this paper, we present a comprehensive survey on neural topic models concerning methods, applications, and challenges.

Survey Topic Models

On the Affinity, Rationality, and Diversity of Hierarchical Topic Modeling

2 code implementations25 Jan 2024 Xiaobao Wu, Fengjun Pan, Thong Nguyen, Yichao Feng, Chaoqun Liu, Cong-Duy Nguyen, Anh Tuan Luu

Hierarchical topic modeling aims to discover latent topics from a corpus and organize them into a hierarchy to understand documents with desirable semantic granularity.

Decoder Diversity +1

READ: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling

1 code implementation12 Dec 2023 Thong Nguyen, Xiaobao Wu, Xinshuai Dong, Khoi Le, Zhiyuan Hu, Cong-Duy Nguyen, See-Kiong Ng, Luu Anh Tuan

Fully fine-tuning pretrained large-scale transformer models has become a popular paradigm for video-language modeling tasks, such as temporal language grounding and video-language summarization.

Language Modeling Language Modelling +1

Towards the TopMost: A Topic Modeling System Toolkit

1 code implementation13 Sep 2023 Xiaobao Wu, Fengjun Pan, Anh Tuan Luu

Topic models have a rich history with various applications and have recently been reinvigorated by neural topic modeling.

Topic Models Variational Inference

Gradient-Boosted Decision Tree for Listwise Context Model in Multimodal Review Helpfulness Prediction

1 code implementation22 May 2023 Thong Nguyen, Xiaobao Wu, Xinshuai Dong, Anh Tuan Luu, Cong-Duy Nguyen, Zhen Hai, Lidong Bing

Multimodal Review Helpfulness Prediction (MRHP) aims to rank product reviews based on predicted helpfulness scores and has been widely applied in e-commerce via presenting customers with useful reviews.

Fact-Checking Complex Claims with Program-Guided Reasoning

2 code implementations22 May 2023 Liangming Pan, Xiaobao Wu, Xinyuan Lu, Anh Tuan Luu, William Yang Wang, Min-Yen Kan, Preslav Nakov

Fact-checking real-world claims often requires collecting multiple pieces of evidence and applying complex multi-step reasoning.

Fact Checking In-Context Learning

Zero-Shot Text Classification via Self-Supervised Tuning

1 code implementation19 May 2023 Chaoqun Liu, Wenxuan Zhang, Guizhen Chen, Xiaobao Wu, Anh Tuan Luu, Chip Hong Chang, Lidong Bing

In this work, we propose a new paradigm based on self-supervised learning to solve zero-shot text classification tasks by tuning the language models with unlabeled data, called self-supervised tuning.

Self-Supervised Learning Sentence +5

InfoCTM: A Mutual Information Maximization Perspective of Cross-Lingual Topic Modeling

2 code implementations7 Apr 2023 Xiaobao Wu, Xinshuai Dong, Thong Nguyen, Chaoqun Liu, Liangming Pan, Anh Tuan Luu

Instead of the direct alignment in previous work, we propose a topic alignment with mutual information method.

Topic Models

Mitigating Data Sparsity for Short Text Topic Modeling by Topic-Semantic Contrastive Learning

2 code implementations23 Nov 2022 Xiaobao Wu, Anh Tuan Luu, Xinshuai Dong

To overcome the data sparsity issue in short text topic modeling, existing methods commonly rely on data augmentation or the data characteristic of short texts to introduce more word co-occurrence information.

Contrastive Learning Data Augmentation

Adaptive Contrastive Learning on Multimodal Transformer for Review Helpfulness Predictions

1 code implementation7 Nov 2022 Thong Nguyen, Xiaobao Wu, Anh-Tuan Luu, Cong-Duy Nguyen, Zhen Hai, Lidong Bing

To overcome the aforementioned issues, we propose Multimodal Contrastive Learning for Multimodal Review Helpfulness Prediction (MRHP) problem, concentrating on mutual information between input modalities to explicitly elaborate cross-modal relations.

Contrastive Learning multimodal interaction

Vision-and-Language Pretraining

1 code implementation5 Jul 2022 Thong Nguyen, Cong-Duy Nguyen, Xiaobao Wu, See-Kiong Ng, Anh Tuan Luu

Moreover, a list of training datasets and downstream tasks is supplied to further polish the perspective into V\&L pretraining.

Diversity image-classification +6

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