6 papers
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…
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…
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…
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…
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…
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…