@article{BudnikovBykovaYamshchikov, author = {Budnikov, Mikhail and Bykova, Anna and Yamshchikov, Ivan}, title = {Generalization potential of large language models}, series = {Neural Computing and Applications}, volume = {37}, journal = {Neural Computing and Applications}, number = {4}, publisher = {Springer}, issn = {0941-0643}, doi = {10.1007/s00521-024-10827-6}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:863-opus-57807}, pages = {1973 -- 1997}, abstract = {The rise of deep learning techniques and especially the advent of large language models (LLMs) intensified the discussions around possibilities that artificial intelligence with higher generalization capability entails. The range of opinions on the capabilities of LLMs is extremely broad: from equating language models with stochastic parrots to stating that they are already conscious. This paper represents an attempt to review LLM landscape in the context of their generalization capacity as an information theoretic property of those complex systems. We discuss the suggested theoretical explanations for generalization in LLMs and highlight possible mechanisms responsible for these generalization properties. Through an examination of existing literature and theoretical frameworks, we endeavor to provide insights into the mechanisms driving the generalization capacity of LLMs, thus contributing to a deeper understanding of their capabilities and limitations in natural language processing tasks.}, language = {en} } @inproceedings{TikhonovShteinerBykovaetal., author = {Tikhonov, Alexey and Shteiner, Sergei and Bykova, Anna and Yamshchikov, Ivan P.}, title = {Smotrom tvoja p{\aa} ander drogoj verden! Resurrecting Dead Pidgin with Generative Models: Russenorsk Case Study}, series = {Findings of the Association for Computational Linguistics: ACL 2025}, booktitle = {Findings of the Association for Computational Linguistics: ACL 2025}, publisher = {Association for Computational Linguistics}, address = {Stroudsburg, PA, USA}, doi = {10.18653/v1/2025.findings-acl.934}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:863-opus-62808}, pages = {18156 -- 18166}, abstract = {Russenorsk, a pidgin language historically used in trade interactions between Russian and Norwegian speakers, represents a unique linguistic phenomenon. In this paper, we attempt to analyze its lexicon using modern large language models (LLMs), based on surviving literary sources. We construct a structured dictionary of the language, grouped by synonyms and word origins. Subsequently, we use this dictionary to formulate hypotheses about the core principles of word formation and grammatical structure in Russenorsk and show which hypotheses generated by large language models correspond to the hypotheses previously proposed ones in the academic literature. We also develop a "reconstruction" translation agent that generates hypothetical Russenorsk renderings of contemporary Russian and Norwegian texts.}, language = {en} }