Evaluating Hallucinations in Large Language Models for Bulgarian Language

Abstract

In this short paper, we introduce the task of evaluating the hallucination of large language models for the Bulgarian language. We first give definitions of what is a hallucination in large language models and what evaluation methods for measuring hallucinations exist. Next, we give an overview of the multilingual evaluation of the latest large language models, focusing on the evaluation of the performance in Bulgarian on tasks, related to hallucination. We then present a method to evaluate the level of hallucination in a given language with no reference data, and provide some initial experiments with this method in Bulgarian. Finally, we provide directions for future research on the topic.