Testing Large Language Models on Minimal Emotional Sentences
Received: 06 Nov 2026 Revised: 07 Nov 2026 Accepted: 09 Nov 2026
Published: 2026, vol. 30, issue 4, pp. 385–388
Abstract
Eight language models classified emotions in minimal Russian sentences. Alice AI LLM and Qwen 3.5-397B-A17B tied in rounded accuracy (0.751). Alice AI LLM had the highest macro-F1 (0.742). Replacing a period with a question mark in affirmative past-tense sentences changed labels more often for each model than for annotators.
Keywords: language models, emotion classification, negation, punctuation, Russian.
BibTeX
@article{IS-Mursalimov-Iaroshenko-Loukachevitch2026,
author = {Mursalimov, Danil and Iaroshenko, Polina V. and Loukachevitch, Natalia Valentinovna},
title = {{Testing Large Language Models on Minimal Emotional Sentences}},
journal = {Intelligent Systems. Theory and Applications},
year = {2026},
volume = {30},
number = {4},
pages = {385--388},
}
AMSBIB
\Bibitem{IS-Mursalimov-Iaroshenko-Loukachevitch2026}
\by D.~Mursalimov, P.\,V.~Iaroshenko, N.\,V.~Loukachevitch
\paper Testing Large Language Models on Minimal Emotional Sentences
\jour Intelligent Systems. Theory and Applications
\yr 2026
\vol 30
\issue 4
\pages 385--388
\lang In Russian
Published under
Creative Commons Attribution 4.0 International (CC BY 4.0)
RU