On the affinity, rationality, and diversity of hierarchical topic modeling
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 …
into a hierarchy to understand documents with desirable semantic granularity. However …
AKEW: Assessing knowledge editing in the wild
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 …
correct and up-to-date. However, its current evaluations deviate significantly from practice …
[HTML][HTML] Topic Modeling for Faster Literature Screening Using Transformer-Based Embeddings
Systematic reviews are a powerful tool to summarize the existing evidence in medical
literature. However, identifying relevant articles is difficult, and this typically involves …
literature. However, identifying relevant articles is difficult, and this typically involves …
Are LLMs good zero-shot fallacy classifiers?
Fallacies are defective arguments with faulty reasoning. Detecting and classifying them is a
crucial NLP task to prevent misinformation, manipulative claims, and biased decisions …
crucial NLP task to prevent misinformation, manipulative claims, and biased decisions …
Towards the topmost: A topic modeling system toolkit
Topic models have been proposed for decades with various applications and recently
refreshed by the neural variational inference. However, these topic models adopt totally …
refreshed by the neural variational inference. However, these topic models adopt totally …
FASTopic: A Fast, Adaptive, Stable, and Transferable Topic Modeling Paradigm
Topic models have been evolving rapidly over the years, from conventional to recent neural
models. However, existing topic models generally struggle with either effectiveness …
models. However, existing topic models generally struggle with either effectiveness …
Antileak-bench: Preventing data contamination by automatically constructing benchmarks with updated real-world knowledge
Data contamination hinders fair LLM evaluation by introducing test data into newer models'
training sets. Existing studies solve this challenge by updating benchmarks with newly …
training sets. Existing studies solve this challenge by updating benchmarks with newly …
Topic Modeling as Multi-Objective Contrastive Optimization
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 …
weighted linear combination of the evidence lower bound (ELBO) of the log-likelihood and …
Uncovering flat and hierarchical topics by Community Discovery on Word Co-occurrence Network
E Austin, S Makwana, A Trabelsi, C Largeron… - Data Science and …, 2024 - Springer
Topic modeling aims to discover latent themes in collections of text documents. It has
various applications across fields such as sociology, opinion analysis, and media studies. In …
various applications across fields such as sociology, opinion analysis, and media studies. In …
Topic modelling through the bibliometrics lens and its technique
B Ogunleye, BS Lancho Barrantes… - Artificial Intelligence …, 2025 - Springer
Topic modelling (TM) is a significant natural language processing (NLP) task and is
becoming more popular, especially, in the context of literature synthesis and analysis …
becoming more popular, especially, in the context of literature synthesis and analysis …