A survey on neural topic models: methods, applications, and challenges

X Wu, T Nguyen, AT Luu - Artificial Intelligence Review, 2024 - Springer
Topic models have been prevalent for decades to discover latent topics and infer topic
proportions of documents in an unsupervised fashion. They have been widely used in …

AKEW: Assessing knowledge editing in the wild

X Wu, L Pan, WY Wang, LA Tuan - Proceedings of the 2024 …, 2024 - aclanthology.org
Abstract Knowledge editing injects knowledge updates into language models to keep them
correct and up-to-date. However, its current evaluations deviate significantly from practice …

On the affinity, rationality, and diversity of hierarchical topic modeling

X Wu, F Pan, T Nguyen, Y Feng, C Liu… - Proceedings of the …, 2024 - ojs.aaai.org
Hierarchical topic modeling aims to discover latent topics from a corpus and organize them
into a hierarchy to understand documents with desirable semantic granularity. However …

Infoctm: A mutual information maximization perspective of cross-lingual topic modeling

X Wu, X Dong, T Nguyen, C Liu, LM Pan… - Proceedings of the AAAI …, 2023 - ojs.aaai.org
Cross-lingual topic models have been prevalent for cross-lingual text analysis by revealing
aligned latent topics. However, most existing methods suffer from producing repetitive topics …

MetaPro 2.0: Computational metaphor processing on the effectiveness of anomalous language modeling

R Mao, K He, C Ong, Q Liu… - Findings of the …, 2024 - aclanthology.org
Metaphor interpretation is a difficult task in natural language understanding. The
development of relevant techniques in this domain is slow, mostly because of the lack of …

Towards the topmost: A topic modeling system toolkit

X Wu, F Pan, AT Luu - arxiv preprint arxiv:2309.06908, 2023 - arxiv.org
Topic models have been proposed for decades with various applications and recently
refreshed by the neural variational inference. However, these topic models adopt totally …

FASTopic: A Fast, Adaptive, Stable, and Transferable Topic Modeling Paradigm

X Wu, T Nguyen, DC Zhang, WY Wang… - arxiv preprint arxiv …, 2024 - arxiv.org
Topic models have been evolving rapidly over the years, from conventional to recent neural
models. However, existing topic models generally struggle with either effectiveness …

Topic Modeling as Multi-Objective Contrastive Optimization

T Nguyen, X Wu, X Dong, CDT Nguyen, SK Ng… - arxiv preprint arxiv …, 2024 - arxiv.org
Recent representation learning approaches enhance neural topic models by optimizing the
weighted linear combination of the evidence lower bound (ELBO) of the log-likelihood and …

Weak-to-Strong Backdoor Attack for Large Language Models

S Zhao, L Gan, Z Guo, X Wu, L **ao, X Xu… - arxiv preprint arxiv …, 2024 - arxiv.org
Despite being widely applied due to their exceptional capabilities, Large Language Models
(LLMs) have been proven to be vulnerable to backdoor attacks. These attacks introduce …

Gradient-boosted decision tree for listwise context model in multimodal review helpfulness prediction

T Nguyen, X Wu, X Dong, AT Luu, CD Nguyen… - arxiv preprint arxiv …, 2023 - arxiv.org
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 …