AIConfPaper
← Search

Viktor Moskvoretskii

7 accepted papers

2025

Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home

Viktor Moskvoretskii, Maria Marina, Mikhail Salnikov, Nikolay Ivanov, Sergey Pletenev, Daria Galimzianova +4
ACL 2025long

Retrieval Augmented Generation (RAG) improves correctness of Question Answering (QA) and addresses hallucinations in Large Language Models (LLMs), yet greatly increase computational costs. Besides, RAG is not always needed as may introduce irrelevant information. Recent adaptive retrieval methods in…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs

Maxim Zhelnin, Viktor Moskvoretskii, Egor Shvetsov, Maria Krylova, Venediktov Egor, Zuev Aleksandr +1
ACL 2025long

Parameter Efficient Fine-Tuning (PEFT) methods have gained popularity and democratized the usage of Large Language Models (LLMs). Recent studies have shown that a small subset of weights significantly impacts performance. Based on this observation, we introduce a novel PEFT method, called Gaussian n…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

LLM-Independent Adaptive RAG: Let the Question Speak for Itself

Maria Marina, Nikolay Ivanov, Sergey Pletenev, Mikhail Salnikov, Daria Galimzianova, Nikita Krayko +3
EMNLP 2025

Large Language Models (LLMs) are prone to hallucinations, and Retrieval-Augmented Generation (RAG) helps mitigate this, but at a high computational cost while risking misinformation. Adaptive retrieval aims to retrieve only when necessary, but existing approaches rely on LLM-based uncertainty estima

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA

Sergey Pletenev, Maria Marina, Nikolay Ivanov, Daria Galimzianova, Nikita Krayko, Mikhail Salnikov +3
EMNLP 2025

Large Language Models (LLMs) often hallucinate in question answering (QA) tasks. A key yet underexplored factor contributing to this is the temporality of questions – whether they are evergreen (answers remain stable over time) or mutable (answers change). In this work, we introduce EverGreenQA, the

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

Are Large Language Models Good at Lexical Semantics? A Case of Taxonomy Learning

Viktor Moskvoretskii, Alexander Panchenko, Irina Nikishina
COLING 2024main

Recent studies on LLMs do not pay enough attention to linguistic and lexical semantic tasks, such as taxonomy learning. In this paper, we explore the capacities of Large Language Models featuring LLaMA-2 and Mistral for several Taxonomy-related tasks. We introduce a new methodology and algorithm for…

Cited by 8Source ↗PDF ↗code ↗Scholar ↗
2024

Low-Resource Machine Translation through the Lens of Personalized Federated Learning

Viktor Moskvoretskii, Nazarii Tupitsa, Chris Biemann, Samuel Horváth, Eduard Gorbunov, Irina Nikishina
EMNLP 2024finding

We present a new approach called MeritOpt based on the Personalized Federated Learning algorithm MeritFed that can be applied to Natural Language Tasks with heterogeneous data. We evaluate it on the Low-Resource Machine Translation task, using the datasets of South East Asian and Finno-Ugric languag…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2024

TaxoLLaMA: WordNet-based Model for Solving Multiple Lexical Semantic Tasks

Viktor Moskvoretskii, Ekaterina Neminova, Alina Lobanova, Alexander Panchenko, Irina Nikishina
ACL 2024long

In this paper, we explore the capabilities of LLMs in capturing lexical-semantic knowledge from WordNet on the example of the LLaMA-2-7b model and test it on multiple lexical semantic tasks. As the outcome of our experiments, we present TaxoLLaMA, the “all-in-one” model for taxonomy-related tasks, l…

Cited by 8Source ↗PDF ↗code ↗Scholar ↗