Author

Maksim Savkin

Observed name: Savkin, Maksim

Observed institution: Moscow Institute of Physics and Technology

ORCID: 0009-0003-5465-2274

Observed ORCID: 0009-0003-5465-2274

OpenAlex ID: A5030369269

SPY: Enhancing Privacy with Synthetic PII Detection Dataset

2025 · Maksim Savkin, Timur Ionov, et al. · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · 7

PDF

When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA

2025 · Elisei Rykov, Kseniia Petrushina, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · 2

PDF

DeepPavlov 1.0: Your Gateway to Advanced NLP Models Backed by Transformers and Transfer Learning

2024 · Maksim Savkin, Anastasia Voznyuk, et al. · Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP) · 2

PDF

Enoki: Efficient Multi-Level Hallucination Detection

2026 · Rykov, Elisei, Ionov, Timur, et al. · arXiv (Cornell University)

PDF

OCC-RAG: Optimal Cognitive Core for Faithful Question Answering

2026 · Savkin, Maksim, Goncharov, Mikhail, et al. · arXiv (Cornell University)

PDF

DeepPavlov Strikes Back: A Toolkit for Improving LLM Reliability and Trustworthiness

2026 · Association for Computational Linguistics 2026, Ionov, Timur, et al. · Underline Science Inc.

DeepPavlov Strikes Back: A Toolkit for Improving LLM Reliability and Trustworthiness

2026 · Evgenii Nikolaev, Timur Ionov, et al. · Conference of the European Chapter of the Association for Computational Linguistics

PDF

Trust the Context, Not the Weights: Faithful Multi-Hop QA via Synthetic Mid-Training

2026 · Maksim Savkin, Mikhail Goncharov, et al. · Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP)

PDF

SHARP: Span-level Hallucination Annotation for Reasoning Paths in Generated Mathematical Solutions

2026 · Timofey Garaev, Makar Gorokhovik, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)

PDF

When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA

2025 · Rykov, Elisei, Petrushina, Kseniia, et al. · arXiv (Cornell University)

PDF

Tuning-Free Discriminative Nearest Neighbor Few-Shot Intent Detection via Consecutive Knowledge Transfer

2024 · Maksim Savkin, Vasily Konovalov · Communications in computer and information science

Works count: 13

Citation count: 11

H-index: 2

I10-index: