Prof. Ivan P. Yamshchikov

My research interests are generative language modeling, human-llm interaction, computational creativity, efficient representation learning of textual data as well as low-resource NLP, especially for dead languages.

• Chizhov P, Arnett C, Korotkova E, Yamshchikov I. BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer Training. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing 2024 Nov (pp. 16587-16604). 10.18653/v1/2024.emnlp-main.925
• Sorokovikova A, Rezagholi S, Fedorova N, Yamshchikov I. LLMs Simulate Big5 Personality Traits: Further Evidence. InProceedings of the 1st Workshop on Personalization of Generative AI Systems (PERSONALIZE 2024) 2024 Mar (pp. 83-87). https://aclanthology.org/2024.personalize-1.7
• Mosin V, Samenko I, Kozlovskii B, Tikhonov A, Yamshchikov IP. Fine-tuning transformers: Vocabulary transfer. Artificial Intelligence. 2023 Apr 1;317:103860. 10.1016/j.artint.2023.103860
• Surkov MK, Yamshchikov IP. Vygotsky Distance: Measure for Benchmark Task Similarity. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) 2024 May (pp. 17409-17420). https://aclanthology.org/2024.lrec-main.1513/