5 papers
MindShift: Analyzing Language Models' Reactions to Psychological Prompts
Anton Vasiliuk, Irina Abdullaeva, Polina Druzhinina +2
Large language models (LLMs) hold the potential to absorb and reflect personality traits and attitudes specified by users. In our study, we investigated this potential using robust…
I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
Andrey Galichin, Alexey Dontsov, Polina Druzhinina +4
Recent LLMs like DeepSeek-R1 have demonstrated state-of-the-art performance by integrating deep thinking and complex reasoning during generation. However, the internal mechanisms b…
Universal Adversarial Attack on Aligned Multimodal LLMs
Temurbek Rahmatullaev, Polina Druzhinina, Nikita Kurdiukov +3
We propose a universal adversarial attack on multimodal Large Language Models (LLMs) that leverages a single optimized image to override alignment safeguards across diverse queries…
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…
LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers
Anton Razzhigaev, Matvey Mikhalchuk, Temurbek Rahmatullaev +4
We introduce methods to quantify how Large Language Models (LLMs) encode and store contextual information, revealing that tokens often seen as minor (e.g., determiners, punctuation…