5 papers
Improving Small Language Models for Code Generation with Reinforcement Learning from Verification Feedback
Egor Skopin, Evgeny Kotelnikov
Reinforcement learning with verifiable rewards (RLVR) trains language models using programmatically checkable signals such as unit-test outcomes, enabling direct optimization for f…
Can LLM Teams Play What? Where? When?
Anastasia Kotelnikova, Viktor Byzov, Maria Dolzhenkova +1
Large language models (LLMs) remain limited on tasks requiring indirect reasoning, cultural knowledge, and coordinated hypothesis testing. We investigate whether team-based interac…
Optimizing Multimodal Language Models through Attention-based Interpretability
Alexander Sergeev, Evgeny Kotelnikov
Modern large language models become multimodal, analyzing various data formats like text and images. While fine-tuning is effective for adapting these multimodal language models (M…
Talking to Data: Designing Smart Assistants for Humanities Databases
Alexander Sergeev, Valeriya Goloviznina, Mikhail Melnichenko +1
Access to humanities research databases is often hindered by the limitations of traditional interaction formats, particularly in the methods of searching and response generation. T…
Do LLMs Understand Why We Write Diaries? A Method for Purpose Extraction and Clustering
Valeriya Goloviznina, Alexander Sergeev, Mikhail Melnichenko +1
Diary analysis presents challenges, particularly in extracting meaningful information from large corpora, where traditional methods often fail to deliver satisfactory results. This…