LLM-based Multilingual Fake News Detection using Cross-Lingual Semantic Alignment and Contextual Reasoning

Multilingual Fake News Detection Using Machine Learning with Contextual-Based Feature Extraction

The proposed approach provides a simple and efficient solution for multilingual fake news detection in data-scarce environments with ensemble-based classifiers such as Random Forest and Gradient Boosting achieving reliable performance across both languages.

A Three-Stage Cross-Lingual Knowledge Transfer Approach Based on the XLM-RoBERTa Model for Detecting Fake News in Ukrainian

In recent years, there has been an increase in the amount of fake news in the media, which is why fact-checking systems are gaining popularity, particularly those that use natural language processing (NLP) to quickly identify and flag fake news. One of the main limitations in the development of such systems is the limited number of datasets containing verified information, which are necessary for the effective training of models. The situation is particularly critical for non-English datasets, specifically those in the Ukrainian language. This article proposes a three-stage algorithm for training a model to recognize fake news in the Ukrainian language. At the core of the proposed approach lies the multilingual transformer model XLM-RoBERTa, which solves this problem by utilizing cross-lingual knowledge transfer from English to Ukrainian. This approach means there is no need to search for a large, high-quality dataset in Ukrainian; instead, a significantly smaller dataset in Ukrainian can be used for the final calibration of the model. The model developed as a result of the experiment proved effective in extreme low-resource scenarios, achieving 90.7% accuracy on just 500 training records and outperforming the baseline model by 9.7%.

Cross-lingual transfer learning for fake news detection: leveraging high-resource language for low-resource adaptation

Cross-Lingual Information Retrieval for Indonesian–Javanese Documents Using LLM-Based Reranking

Cross-lingual information retrieval (CLIR) for low-resource regional languages remains challenging due to limited annotated training data, morphological complexity, and linguistic diversity. This paper systematically investigates Indonesian–Javanese CLIR by integrating traditional sparse lexical retrieval, multilingual dense retrieval, and advanced large language model (LLM)-based reranking within a multi-stage retrieval framework. To evaluate our approach, comprehensive experiments are conducted on the Indonesian–Javanese subset of the CLIRMatrix benchmark, comprising 20,000 Javanese documents, 1,000 Indonesian queries, and 11,000 graded relevance judgments. We compare BM25 with query and document translation, multilingual bi-encoder retrieval, and various LLM-based pointwise reranking methods. The experimental results show that BM25 combined with document translation provides the strongest initial baseline, achieving a Mean Average Precision (MAP) of 0.45, Mean Reciprocal Rank (MRR) of 0.71, and nDCG@10 of 0.55. While LLM-based reranking consistently improves weaker dense retrieval baselines, it often degrades search performance when applied directly on top of strong BM25-based retrieval. To address this, Reciprocal Rank Fusion (RRF) is introduced, which mitigates this degradation issue and achieves the best overall performance, reaching a MAP of 0.47, MRR of 0.74, and nDCG@10 of 0.57. These empirical findings highlight the critical importance of robust initial retrieval baselines and demonstrate that LLM-based reranking is most effective when combined with rank fusion strategies in low-resource CLIR settings.

Bilingual semantic correspondence through knowledge distillation and encoder combination

The challenge of cross-lingual semantic similarity detection is a significant problem in the context of multilingual educational software tools. This paper proposes a novel approach using ensemble learning and knowledge distillation for the development of an efficient and interpretable cross-lingual semantic similarity detection model for the English-French language pair. The methodology is based on the fusion of knowledge from the MiniLM encoder representation using a lightweight attention mechanism, LaBSE encoder with support for language-independent semantic representations, and the BERT encoder with the ability to produce dense contextual vector representations. The knowledge is then distilled using a Multi-Layer Perceptron (MLP) architecture for the development of the semantic similarity detection model. The experimental results show that the ensemble architecture attains a validation F1-score of 0.930, while the knowledge distillation student model retains a robust F1-score of 0.918 with a low computational footprint (3.17M parameters, 42MB memory, 5.77ms inference). This demonstrates the viability of knowledge distillation for the transfer of ensemble-level semantic knowledge into a compact architecture for the context of resource-constrained educational tools.

Cross-Lingual Transfer for Semantic Role Labeling in Indonesian

Semantic role labeling is a semantic analysis task that aims to identify the semantic relationships within a sentence, such as who did what to whom, where, when, and so on. Current semantic role labeling (SRL) models for the Indonesian language still face challenges in achieving strong performance due to the limited availability of annotated corpora, especially compared with English SRL models. Therefore, this paper develops an Indonesian SRL model using cross-lingual transfer. This approach addresses the data scarcity problem in Indonesian SRL by leveraging the availability of annotated English-language corpora. The method uses multilingual models and SRL datasets from both English and Indonesian. The multilingual models used in this study are XLM-R and mT5, both in base and large configurations. The datasets include Universal PropBank Indonesia and Gojali’s dataset for Indonesian, and CoNLL-2012 for English. Evaluation was conducted using test data from Universal PropBank Indonesia and Gojali’s dataset. Among all developed models, XLM-R large with cross-lingual transfer achieved the best performance, with an F1 score of 0.916 on Gojali’s dataset and 0.858 on the combined Universal PropBank Indonesia and Gojali datasets.