What question did this study set out to answer?

The research investigates how well large language models can interpret and translate Bessarabian idioms, focusing on their semantic challenges.

synapse

⌘+K

synapse

⌘+K

February 17, 2026Open Access

Semantic non-compositional exploration of Bessarabian idioms by LLMs

Key Points

The research investigates how well large language models can interpret and translate Bessarabian idioms, focusing on their semantic challenges.
Digitized 1000 Bessarabian proverbs as part of the CI ARiA project.
Evaluated 10 AI models, including ChatGPT and Gemini, using 400 proverbs from the corpus.
Applied multi-algorithmic methodology combining textual distance metrics and semantic similarity analysis.
Models displayed a good ability to understand metaphorical meanings of idioms.
Notable differences in performance regarding consistency and explanatory style among the models.

Abstract

The study explores the potential of LLMs in interpreting and translating Bessarabian idioms. The central problem addressed is the semantic non-compositionality of idiomatic expressions, which poses a significant challenge for Natural Language Processing since their figurative meaning cannot be derived from literal components. As part of the CI ARiA project, 1000 proverbs were digitized, using a corpus of 400 of them to evaluate the performance of 10 AI models (such as ChatGPT, Gemini, Grok). The methodology is multi-algorithmic, combining textual distance metrics (Levenshtein, Jaccard) with semantic similarity analysis via Sentence Transformers. The results indicate that while models demonstrate a solid capacity to grasp metaphorical meanings, significant differences exist regarding consistency and explanatory style.

Semantic non-compositional exploration of Bessarabian idioms by LLMs

Key Points

Abstract

Cite This Study

Also Consider

Also Consider