LLM-XTM: Enhancing Cross-Lingual Topic Models with Large Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909013539553280 |
|---|---|
| author | Xuan, Minh Chu Nguyen, Tien-Phat Van, Linh Ngo Sang, Dinh Viet Diep, Nguyen Thi Ngoc Le, Trung |
| author_facet | Xuan, Minh Chu Nguyen, Tien-Phat Van, Linh Ngo Sang, Dinh Viet Diep, Nguyen Thi Ngoc Le, Trung |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_03299 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LLM-XTM: Enhancing Cross-Lingual Topic Models with Large Language Models Xuan, Minh Chu Nguyen, Tien-Phat Van, Linh Ngo Sang, Dinh Viet Diep, Nguyen Thi Ngoc Le, Trung Computation and Language 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. |
| title | LLM-XTM: Enhancing Cross-Lingual Topic Models with Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2605.03299 |