AIConfPaper
← Search

Irina Nikishina

8 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

CompUGE-Bench: Comparative Understanding and Generation Evaluation Benchmark for Comparative Question Answering

Ahmad Shallouf, Irina Nikishina, Chris Biemann
COLING 2025system demonstrations

This paper presents CompUGE, a comprehensive benchmark designed to evaluate Comparative Question Answering (CompQA) systems. The benchmark is structured around four core tasks: Comparative Question Identification, Object and Aspect Identification, Stance Classification, and Answer Generation. It uni…

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

How to Compare Things Properly? A Study of Argument Relevance in Comparative Question Answering

Irina Nikishina, Saba Anwar, Nikolay Dolgov, Maria Manina, Daria Ignatenko, Artem Shelmanov +1
ACL 2025long

Comparative Question Answering (CQA) lies at the intersection of Question Answering, Argument Mining, and Summarization. It poses unique challenges due to the inherently subjective nature of many questions and the need to integrate diverse perspectives. Although the CQA task can be addressed using r…

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

CAM 2.0: End-to-End Open Domain Comparative Question Answering System

Ahmad Shallouf, Hanna Herasimchyk, Mikhail Salnikov, Rudy Alexandro Garrido Veliz, Natia Mestvirishvili, Alexander Panchenko +2
COLING 2024main

Comparative Question Answering (CompQA) is a Natural Language Processing task that combines Question Answering and Argument Mining approaches to answer subjective comparative questions in an efficient argumentative manner. In this paper, we present an end-to-end (full pipeline) system for answering…

Cited by 3Source ↗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 ↗
2020

Studying Taxonomy Enrichment on Diachronic WordNet Versions

Irina Nikishina, Varvara Logacheva, Alexander Panchenko, Natalia Loukachevitch
COLING 2020main

Ontologies, taxonomies, and thesauri have always been in high demand in a large number of NLP tasks. However, most studies are focused on the creation of lexical resources rather than the maintenance of the existing ones and keeping them up-to-date. In this paper, we address the problem of taxonomy…

Cited by 16Source ↗PDF ↗code ↗Scholar ↗