5 papers
Data-Centric Post-Training for Financial Reasoning: Mining, Distillation, and Verifiable Learning
Zhirayr Hayrapetyan, Andrei Kalmykov, Denis Kokosinskii +2
Financial text, textbooks, and question-answer pairs are abundant, but only a small fraction is directly usable for reasoning-focused post-training. Existing QA pairs often lack ex…
FINESSE-Bench: A Hierarchical Benchmark Suite for Financial Domain Knowledge and Technical Analysis in Large Language Models
Dmitry Stanishevskii, Nini Kamkia, Alexey Khoroshilov +4
Large language models (LLMs) are increasingly being applied to financial analysis, reporting, investment decision support, risk management, compliance, and professional training. H…
Deep-change at AXOLOTL-24: Orchestrating WSD and WSI Models for Semantic Change Modeling
Denis Kokosinskii, Mikhail Kuklin, Nikolay Arefyev
This paper describes our solution of the first subtask from the AXOLOTL-24 shared task on Semantic Change Modeling. The goal of this subtask is to distribute a given set of usages…
Multilingual Substitution-based Word Sense Induction
Denis Kokosinskii, Nikolay Arefyev
Word Sense Induction (WSI) is the task of discovering senses of an ambiguous word by grouping usages of this word into clusters corresponding to these senses. Many approaches were…
Calculating entropy by Ma's method for a system of -mers on a square lattice
Denis V Kokosinskii, Mikhail V Ulyanov
Boltzmann's entropy is an important feature of any dynamic system. Calculating Boltzmann's entropy directly as the logarithm of the total number of microstates for a current macros…