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

TL;DR

LLM-XTM is a novel framework that improves cross-lingual topic models by integrating large language models for refinement, achieving better coherence and alignment with less resource dependence.

Contribution

It introduces a black-box, scalable method combining LLM-guided refinement with uncertainty quantification for cross-lingual topic modeling.

Findings

Achieves superior topic coherence and alignment on multilingual corpora.

Reduces reliance on bilingual dictionaries and costly LLM calls.

Provides a stable, scalable enhancement framework for cross-lingual topics.

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.