Vladimir Sergeevich Skvortsov

Vladimir Sergeevich Skvortsov

Saint Petersburg National Research University of Information Technologies, Mechanics and Optics, Saint Petersburg, Sankt-Peterburg, Russia
orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
VSVladimir Sergeevich Skvortsov
Vladimir Sergeevich Skvortsov
Ivan ZolinIvan Zolin
Ivan Zolin
Viacheslav Sergeevich ChukanovViacheslav Sergeevich Chukanov
Viacheslav Sergeevich Chukanov
EPEkaterina Pchitskaya
Ekaterina Pchitskaya
In biomedicine, answers must be complete, current and verifiable, yet a general-purpose large language model (LLM) can give confident but wrong or outdated answers with no sources to check. We present NeuroRAG, a multi-agent retrieval-augmented system that answers neurobiology questions using retrieved scientific sources. Its knowledge base combines a hierarchical index of neurobiology textbooks with live search of PubMed, arXiv, bioRxiv/medRxiv and NCBI Gene/Protein sources, and web search as a fallback. A router selects the sources, query-rewriting agents reformulate the question, passages are fused, reranked and compressed, three LLMs draft answers, which are merged, and, as the last step, graders check grounding in the retrieved text and relevance to the question. On benchmarks, NeuroRAG had the highest accuracy on seven of nine MMLU subsets; on PubMed Summary QA, its similarity to reference answers was comparable to Llama 3.3 70B and lower than GPT-4o and GPT-4.1. Against two published RAG pipelines, it beat FlashRAG Naive RAG on six of seven metrics and was indistinguishable from MedRAG. Because such benchmarks are limited to text and age quickly, we ran a blind evaluation of the system by 14 evaluators: NeuroRAG was chosen in 64.4%, GPT-5 in 14.1%, Claude 4.5 Sonnet in 11.0%, and none in 10.4%. This shows expert preference for NeuroRAG over the other models, though not a direct measure of factual correctness.

20 April 2025 in Computer tools in education
Verified
Journal Article
Open access
PDF file
МАМихаил Ильдусович Аптуков
Михаил Ильдусович Аптуков
МММихаил Денисович Марков
Михаил Денисович Марков
ФНФёдор Александрович Новиков
Фёдор Александрович Новиков
ДПДанил Денисович Пестряков
Данил Денисович Пестряков
VSVladimir Sergeevich Skvortsov
Vladimir Sergeevich Skvortsov
ИХИльсаф Ильназович Хамидуллин
Ильсаф Ильназович Хамидуллин
This paper presents the ONTOL V1 ontology description language. With the help of ONTOL V1 notation it is possible to record ontologies applicable in the educational process in a formalised form. In the course of the work, a grammar of the ONTOL V1 language was developed, as well as its parser. The developed software tool provides the user with the following capabilities: recording ontologies in the form of formalised text; machinereadable representation of ontologies; modularity in describing ontologies of subject areas; visualisation of ontology elements.