collaborators

5 papers

cs.CL2026

ReDAct: Uncertainty-Aware Deferral for LLM Agents

Dzianis Piatrashyn, Nikita Kotelevskii, Kirill Grishchenkov +7

Recently, LLM-based agents have become increasingly popular across many applications, including complex sequential decision-making problems. However, they inherit the tendency of L…

cs.AI2025

ReProbe: Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models

Jingwei Ni, Ekaterina Fadeeva, Tianyi Wu +8

LLMs can solve complex tasks by generating long, multi-step reasoning chains. Test-time scaling (TTS) can further improve performance by sampling multiple variants of intermediate…

cs.CL2025

A Head to Predict and a Head to Question: Pre-trained Uncertainty Quantification Heads for Hallucination Detection in LLM Outputs

Artem Shelmanov, Ekaterina Fadeeva, Akim Tsvigun +9

Large Language Models (LLMs) have the tendency to hallucinate, i.e., to sporadically generate false or fabricated information. This presents a major challenge, as hallucinations of…

cs.CL2025

Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval Augmented Generation

Ekaterina Fadeeva, Aleksandr Rubashevskii, Dzianis Piatrashyn +7

Large Language Models (LLMs) enhanced with retrieval, an approach known as Retrieval-Augmented Generation (RAG), have achieved strong performance in open-domain question answering.…

cs.CL2025

Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Models

Artem Vazhentsev, Lyudmila Rvanova, Ivan Lazichny +4

Uncertainty quantification (UQ) is a prominent approach for eliciting truthful answers from large language models (LLMs). To date, information-based and consistency-based UQ have b…