CV

NLP Research Engineer (full-time)

Huawei Noah's Ark Lab

• Investigated LLM tool usage capabilities. Developed a fine-tuning strategy for error recovery, leading to a publication at the ACL 2025 REALM Workshop.
• Conducted research on multimodal (Text-Video) retrieval, contributing to video retrieval post-processing techniques published at SIGIR 2023.
• Designed and co-implemented the end-to-end NLU pipeline for a production car voice assistant in Russian.

NLP Research Intern (full-time)

Huawei Noah's Ark Lab

• Co-developed and optimized the reranking algorithm for a large-scale product search engine in Russian.
• Improved the reranker model quality by 5% and reduced its inference latency by 1.5x by adapting novel architectural (ColBERTer) and distillation approaches (TinyBERT).

PhD

University of Tübingen & Max Planck Research School

Computer Science

• Health-NLP Lab, Supervisor: Prof. Dr. Carsten Eickhoff.
• Affiliated Scholar, International Max Planck Research School for Intelligent Systems (IMPRS-IS).
• Research topics: Interpretability of Deep Learning Models for NLP and IR tasks.

MSc

Moscow Institute of Physics and Technology

Applied Mathematics and Computer Science

• GPA: 3.35 / 4.00
• Research topics: Sparse Retrieval, Multimodal Retrieval, Tool Calling in LLMs.
• Thesis: “Approaches to Training Language Models for External Function Calling: Using Self-Generated Data for Better Error Detection and Recovery”.

BSc

Moscow Institute of Physics and Technology

Applied Mathematics and Computer Science

• GPA: 3.48 / 4.00
• Thesis: “Usage of MCMC Methods in Deep Learning”.

Understanding Wacky Weights: A Dissection of SPLADE's Learned Term Importance

G. Polyakov, H. Scells, C. Eickhoff

SIGIR 2026

Interpretability Analysis of Arithmetic In-Context Learning in Large Language Models

G. Polyakov, C. Hepting, C. Eickhoff, A. Bahrainian

EMNLP 2025

Towards Best Practices of Axiomatic Activation Patching in Information Retrieval

G. Polyakov, C. Chen, C. Eickhoff

SIGIR 2025

ToolReflection: Improving Large Language Models for Real-World API Calls with Self-Generated Data

G. Polyakov, I. Alimova, D. Abulkhanov, I. Sedykh, A. Bout, S. Nikolenko, I. Piontkovskaya

ACL 2025 REALM Workshop

Sinkhorn Transformations for Single-Query Postprocessing in Text-Video Retrieval

K. Yakovlev, G. Polyakov, I. Alimova, A. V. Podolskiy, A. Bout, S. I. Nikolenko, I. Piontkovskaya

SIGIR 2023

Presidential Grant Scholarship

Russian Federation

Selected as one of 1,200 recipients nationwide for this highly competitive prize recognizing high academic merit and strong participation in competitions. Included a full 4-year stipend supporting undergraduate research and studies.

Teaching Assistant: Modern Search Engines

University of Tübingen

Summer Semesters 2025 and 2026. Conducted hands-on tutorials, evaluated assignments, and mentored student projects.

Teaching Assistant: Introduction to Python Programming

University of Tübingen

Winter Semesters 2024/25 and 2025/26. Conducted hands-on tutorials and evaluated student assignments.