activity
20242026
collaborators

6 papers

cs.LG2026

Think Shallow, Solve Deep: Controlling Recurrent Dynamics for Reliable Test-Time Depth

Ivan Viakhirev, Kirill Borodin, Amirah Almutairi +3

Recurrent-depth reasoners aim to solve harder problems by iterating their update longer at test time, but additional iterations can improve, preserve, or degrade an answer. We show…

cs.CL2026

Hallucination Detection in LLMs with Topological Divergence on Attention Graphs

Alexandra Bazarova, Andrei Volodichev, Aleksandr Yugay +10

Hallucination, i.e., generating factually incorrect content, remains a critical challenge for large language models (LLMs). We introduce TOHA, a TOpology-based HAllucination detect…

cs.CL2025

Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders

Kristian Kuznetsov, Laida Kushnareva, Polina Druzhinina +5

Artificial Text Detection (ATD) is becoming increasingly important with the rise of advanced Large Language Models (LLMs). Despite numerous efforts, no single algorithm performs co…

cs.CL2025

Quantifying Logical Consistency in Transformers via Query-Key Alignment

Eduard Tulchinskii, Anastasia Voznyuk, Laida Kushnareva +4

Large language models (LLMs) have demonstrated impressive performance in various natural language processing tasks, yet their ability to perform multi-step logical reasoning remain…

cs.CL2024

Robust AI-Generated Text Detection by Restricted Embeddings

Kristian Kuznetsov, Eduard Tulchinskii, Laida Kushnareva +4

Growing amount and quality of AI-generated texts makes detecting such content more difficult. In most real-world scenarios, the domain (style and topic) of generated data and the g…

cs.CL2024

Listening to the Wise Few: Select-and-Copy Attention Heads for Multiple-Choice QA

Eduard Tulchinskii, Laida Kushnareva, Kristian Kuznetsov +5

A standard way to evaluate the abilities of LLM involves presenting a multiple-choice question and selecting the option with the highest logit as the model's predicted answer. Howe…