Cross-lingual topic modeling aims to discover shared semantic structures across languages, yet existing models depend on sparse bilingual resources and often yield incoherent or weakly aligned topics. Recent LLM-based refinements improve interpretability but are costly, document-level, and prone to hallucination, with prior white-box approaches requiring inaccessible token probabilities. We propose LLM-XTM, a framework that integrates LLM-guided topic refinement with self-consistency uncertainty quantification, enabling black-box, stable, and scalable enhancement of cross-lingual topic models. Experiments on multilingual corpora show that LLM-XTM achieves superior topic coherence and alignment while reducing reliance on bilingual dictionaries and expensive LLM calls.
@article{arxiv.2605.03299,
title = {LLM-XTM: Enhancing Cross-Lingual Topic Models with Large Language Models},
author = {Minh Chu Xuan and Tien-Phat Nguyen and Linh Ngo Van and Dinh Viet Sang and Nguyen Thi Ngoc Diep and Trung Le},
journal= {arXiv preprint arXiv:2605.03299},
year = {2026}
}