Публикации

2025
Kurtukova A., Kozachenko A., 2025. Backtranslation Invariance Boosts Effectiveness of Non-English Prompts. Computational Linguistics and Intellectual Technologies: Proceedings of the International Conference “Dialogue 2025”, Moscow

We present an approach to improving non-English prompts based on […] ...

2025
Alibekov A., Matenkov A., Bolshakov V., Mukhtarova G., Migal A., Muryshev A., Kozachenko A., Mikhaylovskiy N., 2025. RuTaR—A Dataset in Russian for Reasoning about Taxes. Proceedings of the International Conference “Dialogue 2025″, Moscow

In 2024, reasoning have emerged as a new frontier for […] ...

2025
Chaunin V., Mikhaylovskiy N., 2025. Matrix Mixture of Experts is the best fast feed-forward. MathAI, Tomsk

We dissect the recently introduced Fast Feed-Forward (FFF) neural network […] ...

2024
Migal A., Seredina D., Telnina L., Nazarov N., Kolmogorova A., Mikhaylovskiy N., 2024. Overview of Long Story Generation Challenge (LSGC) at INLG 2024. In Natural Language Generation: Proceedings of the 17th International Conference on Natural Language Generation (INLG 2024), Tokyo.

This report describes the setup and results of the shared task of human-like long story generation, the LSG Challenge, which asks to generate a consistent, human-like long story (a Harry Potter fanfic in English for a general audience) given a prompt of about 1,000 tokens. We evaluated the submissions using both automated metrics and human evaluation protocols. ...

2024
A. Romanovskii., 2024. Digital transformation of the metallurgical industry. Development and integration of the digital twin of the ore pretreatment shop. Mineral Mining & Conservation, 2024, Moscow

В статье рассматривается пример внедрения системы цифрового двойника цеха рудоподготовки […] ...

2023
Mikhaylovskiy N., 2023. Long Story Generation Challenge. In Proceedings of the 16th International Natural Language Generation Conference: Generation Challenges, pages 10–16, Prague, Czechia. Association for Computational Linguistics.

We propose a shared task of human-like long story generation, LSG Challenge, that asks models to output a consistent human-like long story (a Harry Potter generic audience fanfic in English), given a prompt of about 1K tokens. We suggest a novel statistical metric of the text structuredness, GloVe Autocorrelations Power/ Exponential Law Mean Absolute Percentage Error Ratio (GAPELMAPER) and the use of previously-known UNION metric and a human evaluation protocol. We hope that LSG can open new avenues for researchers to investigate sampling approaches, prompting strategies, autoregressive and non-autoregressive text generation architectures and break the barrier to generate consistent long (40K+ word) texts. ...