English

LLM-XTM: Enhancing Cross-Lingual Topic Models with Large Language Models

Computation and Language 2026-05-06 v1

Abstract

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.

Keywords

Cite

@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}
}

Comments

ACL 2026

R2 v1 2026-07-01T12:49:44.473Z