We present a multilingual study of sentiment evaluation on Wikipedia articles from various topics in five languages (German, English,Spanish, Polish, and Russian). In this paper, we compare three large language models (Gemini Pro 3.1, Claude Opus 4.6, and GPT 5.2),each queried three times per sentence, with two popular multilingual sentiment classifiers. This setup allows us to analyze not only inter-model differences but also intra-model stability as a proxy for confidence.To support systematic evaluation, we construct a benchmark dataset based on strict consensus across evaluators and analyze sentiment distributions across topics and languages. We show substantial variation in sentiment distributions, agreement, and consistency across models and languages. Our results suggest that sentiment evaluation on encyclopedic text remains an underexplored challenge for multilingual NLP.

In this work, we investigate whether data annotation can be automated using state-of-the-art large language models (LLMs), while maintaining high consistency and reliability. We propose a multi-model, multi-run framework in which several LLMs act as annotators and their outputs are aggregated using a strict consensus criterion to improve annotation robustness and reduce model-specific biases.

The proposed approach is evaluated on a multilingual sentiment analysis task using lead sections of Wikipedia articles covering diverse topics in five languages. The resulting annotations are assessed using intra-model consistency, cross-model agreement, and standard inter-annotator agreement metrics. Additionally, we conducted human evaluation.

The described framework enables scalable and reproducible data annotation, and the resulting dataset is publicly released to support further research.