• A
  • A
  • A
  • АБВ
  • АБВ
  • АБВ
  • A
  • A
  • A
  • A
  • A
Обычная версия сайта
  • RU
  • EN
  • HSE University
  • Publications
  • Book chapter
  • Lacuna Inc. at SemEval-2025 Task 4: LoRA-Enhanced Influence-Based Unlearning for LLMs
  • RU
  • EN
Расширенный поиск
Высшая школа экономики
Национальный исследовательский университет
Priority areas
  • business informatics
  • economics
  • engineering science
  • humanitarian
  • IT and mathematics
  • law
  • management
  • mathematics
  • sociology
  • state and public administration
by year
  • 2028
  • 2027
  • 2026
  • 2025
  • 2024
  • 2023
  • 2022
  • 2021
  • 2020
  • 2019
  • 2018
  • 2017
  • 2016
  • 2015
  • 2014
  • 2013
  • 2012
  • 2011
  • 2010
  • 2009
  • 2008
  • 2007
  • 2006
  • 2005
  • 2004
  • 2003
  • 2002
  • 2001
  • 2000
  • 1999
  • 1998
  • 1997
  • 1996
  • 1995
  • 1994
  • 1993
  • 1992
  • 1991
  • 1990
  • 1989
  • 1988
  • 1987
  • 1986
  • 1985
  • 1984
  • 1983
  • 1982
  • 1981
  • 1980
  • 1979
  • 1978
  • 1977
  • 1976
  • 1975
  • 1974
  • 1973
  • 1972
  • 1971
  • 1970
  • 1969
  • 1968
  • 1967
  • 1966
  • 1965
  • 1964
  • 1963
  • 1958
  • More
Subject
News
October 1, 2026
HSE Researchers Show How Congenital Motor Disorders Affect Brain Development
Researchers from HSE University’s Institute for Cognitive Neuroscience have synthesised the findings of their previous studies on brain development in children with obstetric brachial plexus palsy and arthrogryposis. Their analysis shows that impaired motor function in early childhood not only limits children’s motor experience but also affects memory, categorical thinking, and information processing. The study has been published in Frontiers in Psychology.
October 1, 2026
Window into the Body: Scientists Develop Neural Network to Detect Risk of 15 Diseases from Retinal Images
Russian universities, with the participation of HSE University, Sber, and Z-union, have developed a neural network that can simultaneously assess the risk of 15 types of pathology from retinal photographs, including not only eye diseases but also cardiovascular conditions. The AI system can help clinicians detect potentially concerning changes at an early stage, identify signs reflecting the condition of retinal blood vessels, and determine whether a patient may need further examination. The paper has been published in Frontiers in Medicine.
September 30, 2026
'We Did Not Limit the Time for Questions'
The International Laboratory for Supercomputer Atomistic Modelling and Multi-Scale Analysis at HSE University held a major conference on molecular dynamics. Participants had the opportunity to attend all the presentations, while speakers were given as much time as they needed to answer questions. The HSE News Service interviewed Grigory Smirnov, Head of the Laboratory, and Genri Norman, Chief Research Fellow, about the conference preparations and the discussions it generated.

 

Have you spotted a typo?
Highlight it, click Ctrl+Enter and send us a message. Thank you for your help!

Publications
  • Books
  • Articles
  • Chapters of books
  • Working papers
  • Report a publication
  • Research at HSE

?

Lacuna Inc. at SemEval-2025 Task 4: LoRA-Enhanced Influence-Based Unlearning for LLMs

P. 1528–1533.
Kudelya A., Shirnin A.

This paper describes LIBU (LoRA enhanced influence-based unlearning), an algorithm to solve the task of unlearning - removing specific knowledge from a large language model without retraining from scratch and compromising its overall utility (SemEval-2025 Task 4: Unlearning sensitive content from Large Language Models). The algorithm combines classical influence functions to remove the influence of thedata from the model and second-order optimization to stabilize the overall utility. Our experiments show that this lightweight approach is well applicable for unlearning LLMs in different kinds of task.

Language: English
Full text
Text on another site
Keywords: Natural Language Processing (NLP)Natural Language Processing (NLP)
Publication based on the results of:
Complex language and semantic models in artificial intelligence (2025)

In book

Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)
Association for Computational Linguistics, 2025.
Similar publications
Lacuna Inc. at SemEval-2026 Task 4: Structurally Gated State-Space Models for Disentangling Narrative Similarity
Куделя А. В., Алшауи Р., Shirnin A., , in: Proceedings of the 20th International Workshop on Semantic Evaluation (2026).: Association for Computational Linguistics, 2026. P. 2347–2353.
In this paper, we present the Invariant-Variant Disentangled State-Space Model (IVD-SSM),our submission to SemEval-2026 Task 4 on Narrative Story Similarity and Narrative Representation Learning. Evaluating narrative similarity is a profound computational challenge that requires models to look past concrete, superficial elements such as specific names, actors, objects, or settings to isolate and compareabstract patterns of ...
Added: September 28, 2026
The Classics at SemEval-2026 Task 3: Combining Transformer Models and LLM-Generated Annotations for Dimensional Aspect-Based Sentiment Analysis
Алшауи Р., Raj A., Куделя А. В. et al., , in: Proceedings of the 20th International Workshop on Semantic Evaluation (2026).: Association for Computational Linguistics, 2026. P. 2648–2656.
This paper presents an approach to the SemEval-2026 Task 3: Dimensional Aspect-Based Sentiment Analysis. We investigate methods for moving beyond traditional categorical sentiment (e.g., positive or negative) to predict fine-grained, real-valued scores for sentiment “valence” (positivity) and “arousal” (intensity). We participate in two subtasks: predicting these scores for given aspects (Subtask 1) and extracting full ...
Added: September 28, 2026
Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
Association for Computational Linguistics, 2026.
Added: September 28, 2026
Lecture Notes in Artificial Intelligence
Springer, 2026.
Two volumes of the SPECOM 2026 proceedings contain a collection of submitted papers presented at SPECOM 2026, which were thoroughly reviewed by members of the Program Committee and additional reviewers consisting of almost 80 experts in the conference topic areas. In total, 65 regular full papers out of 99 submissions made via the EasyChair electronic ...
Added: September 20, 2026
Компьютерная лингвистика и интеллектуальные технологии: По материалам ежегодной международной конференции «Диалог». Выпуск 24
M.: Max press, 2026.
The volume includes 64 papers from the international conference on computational linguistics and intelligent technologies 'Dialogue 2026,' representing a broad spectrum of theoretical and applied research in the field of natural language description, language process modeling, and the development of practically applicable computational linguistic technologies. For specialists in theoretical and applied linguistics and intelligent technologies. ...
Added: June 27, 2026
Proceedings of the Sixth Workshop on Teaching NLP (TeachNLP 2024)
Association for Computational Linguistics, 2024.
Added: June 14, 2026
Analysis of Images, Social Networks and Texts. AIST 2024
Cham: Springer, 2024.
Added: June 14, 2026
Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
Association for Computational Linguistics, 2026.
Added: June 13, 2026
A textual fingerprint learning model to detect fake information spreaders in social networks
Behzadidoost R., Neurocomputing 2025 Vol. 665 P. 1–21
While earlier research has focused on detecting misinformation content, identifying the users who spread it, referred to in this paper as fake information spreaders, remains a relatively new challenge. These users deliberately mix true and false information, making detection more difficult. This paper proposes a textual fingerprint learning model to detect fake information spreaders. The ...
Added: March 12, 2026
SynEL: A synthetic benchmark for entity linking
Karpov I., Kirillovich A., Goncharova E. et al., Plos One 2026 Vol. 21 No. 1 Article e0339468
Large language models (LLMs) offer significant potential for constructing commonsense knowledge graphs from text, demonstrating adaptability across diverse domains. However, their effectiveness varies significantly with domain-specific language, highlighting a critical need for specialized benchmarks to assess and optimize knowledge graph construction sub-tasks like named entity recognition, relation extraction, and entity linking. Currently, domain-specific benchmarks are ...
Added: January 15, 2026
Proceedings of the 39th Annual AAAI Conference on Artificial Intelligence
Washington, United States of America: AAAI Press, 2025.
AAAI-25 Technical Tracks 23 (Natural Language Processing II) collects peer-reviewed research papers that advance the state of natural language processing, with an emphasis on large language models, efficient inference, instruction following, retrieval augmentation, and multimodal language understanding. The papers address both theoretical and practical challenges, including model efficiency, interactive generation, grounding in external knowledge and ...
Added: December 18, 2025
Empaths at SemEval-2025 Task 11: Retrieval-Augmented Approach to Perceived Emotions Prediction
Morozov L., Mogilevskii A., Shirnin A., , in: Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025).: Association for Computational Linguistics, 2025. P. 2000–2007.
This paper describes LIBU (LoRA enhanced influence-based unlearning), an algorithm to solve the task of unlearning - removing specific knowledge from a large language model without retraining from scratch and compromising its overall utility (SemEval-2025 Task 4: Unlearning sensitive content from Large Language Models). The algorithm combines classical influence functions to remove the influence of ...
Added: November 17, 2025
Findings of the Association for Computational Linguistics: EMNLP 2025
Association for Computational Linguistics, 2025.
The book contains this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first workshop, which had 14 accepted papers. As the field ...
Added: November 16, 2025
Findings of the Association for Computational Linguistics: NAACL 2025
Association for Computational Linguistics, 2025.
Added: November 6, 2025
Explainable Document Classification via Concept Whitening and Stable Graph Patterns
Parakal E. G., Kuznetsov S., Makarov I. et al., IEEE Access 2025 Vol. 13 P. 149657–149678
This paper proposes a novel explainable document classification framework that integrates Concept Whitening (CW) with graph concepts that are derived from stable graph patterns, and extracted via methods based on Formal Concept Analysis (FCA) and pattern structures. Document graphs are constructed using Abstract Meaning Representation (AMR) graphs, from which graph concepts are extracted and aligned ...
Added: October 22, 2025
Building a Clean Bartangi Language Corpus and Training Word Embeddings for Low-Resource Language Modeling
Shumen: INCOMA Ltd, 2025.
This paper introduces a rule-based lemmatization and word embedding pipeline for the endangered Bartangi language, part of the Pamiri language group. The system combines a manually constructed lemma dictionary with morphological suffix rules to improve linguistic consistency in low-resource settings. The results demonstrate enhanced lemmatization accuracy and higher-quality embeddings for downstream NLP tasks. The work ...
Added: October 20, 2025
Исследования благополучия с помощью передовых методов обработки естественного языка (NLP): перспективы и ограничения
Voevodina E., Современная зарубежная психология 2025 Т. 14 № 3 С. 172–181
Context and relevance. Well-being research faces methodological limitations of conventional psychometric measures, criticized for poor ecological validity, limited information yield, and inadequate capture of multidimensional construct of well-being. Advanced natural language processing (NLP) technologies offer solutions to these constraints. Objective. To evaluate opportunities and challenges of transformer-based NLP for well-being research. Methods and materials. We conducted an analytical review of ...
Added: October 9, 2025
CLEF 2025 Working Notes
CEUR Workshop Proceedings, 2025.
Added: October 6, 2025
Разработка архитектуры классификатора для оценки состояния объектов инфраструктуры с применением нейронных сетей
Moiseev N., Абрамов И. А., Камакин А. Ю., В кн.: Параллельные вычислительные технологии – XIX всероссийская конференция с международным участием, ПаВТ'2025, г. Москва, 8–10 апреля 2025 г. Короткие статьи и описания плакатов.: Челябинск: Издательский центр ЮУрГУ, 2025. С. 301–301.
In recent years, with the advancement of deep learning and neural network methods, their application in geospatial analysis tasks has become particularly relevant. A key challenge in this field is assessing the state of urban infrastructure, including the classification of buildings by their functional purpose (residential, commercial, governmental, industrial). The use of neural networks significantly ...
Added: September 17, 2025
  • About
  • About
  • Key Figures & Facts
  • Sustainability at HSE University
  • Faculties & Departments
  • International Partnerships
  • Faculty & Staff
  • HSE Buildings
  • HSE University for Persons with Disabilities
  • Public Enquiries
  • Studies
  • Admissions
  • Programme Catalogue
  • Undergraduate
  • Graduate
  • Exchange Programmes
  • Summer University
  • Summer Schools
  • Semester in Moscow
  • Business Internship
  • Research
  • International Laboratories
  • Research Centres
  • Research Projects
  • Monitoring Studies
  • Conferences & Seminars
  • Academic Jobs
  • Yasin (April) International Academic Conference on Economic and Social Development
  • Media & Resources
  • Publications by staff
  • HSE Journals
  • Publishing House
  • iq.hse.ru: commentary by HSE experts
  • Library
  • Economic & Social Data Archive
  • Video
  • HSE Repository of Socio-Economic Information
  • HSE1993–2026
  • Contacts
  • Copyright
  • Privacy Policy
  • Site Map
Edit