AIConfPaper
← Search

Irina Piontkovskaya

12 accepted papers

2025

Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders

Kristian Kuznetsov, Laida Kushnareva, Anton Razzhigaev, Polina Druzhinina, Anastasia Voznyuk, Irina Piontkovskaya +2
ACL 2025finding

Artificial Text Detection (ATD) is becoming increasingly important with the rise of advanced Large Language Models (LLMs). Despite numerous efforts, no single algorithm performs consistently well across different types of unseen text or guarantees effective generalization to new LLMs. Interpretabili…

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

Quantifying Logical Consistency in Transformers via Query-Key Alignment

Eduard Tulchinskii, Laida Kushnareva, Anastasia Voznyuk, Andrei Andriiainen, Irina Piontkovskaya, Evgeny Burnaev +1
EMNLP 2025

Large language models (LLMs) excel at many NLP tasks, yet their multi-step logical reasoning remains unreliable. Existing solutions such as Chain-of-Thought prompting generate intermediate steps but provide no internal check of their logical coherence. In this paper, we use the “QK-score”, a lightwe

Cited by 0Source ↗PDF ↗Scholar ↗
2024

Robust AI-Generated Text Detection by Restricted Embeddings

Kristian Kuznetsov, Eduard Tulchinskii, Laida Kushnareva, German Magai, Serguei Barannikov, Sergey Nikolenko +1
EMNLP 2024finding

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 generator model are not known in advance. In this work, we focus on the robustness of classifier-based detectors of AI-ge…

Cited by 4Source ↗PDF ↗code ↗Scholar ↗
2023

Efficient Grammatical Error Correction Via Multi-Task Training and Optimized Training Schedule

Andrey Bout, Alexander Podolskiy, Sergey Nikolenko, Irina Piontkovskaya
EMNLP 2023long main

Progress in neural grammatical error correction (GEC) is hindered by the lack of annotated training data. Sufficient amounts of high-quality manually annotated data are not available, so recent research has relied on generating synthetic data, pretraining on it, and then fine-tuning on real datasets…

Cited by 0Source ↗Scholar ↗
2023

GEC-DePenD: Non-Autoregressive Grammatical Error Correction with Decoupled Permutation and Decoding

Konstantin Yakovlev, Alexander Podolskiy, Andrey Bout, Sergey Nikolenko, Irina Piontkovskaya
ACL 2023long

Grammatical error correction (GEC) is an important NLP task that is currently usually solved with autoregressive sequence-to-sequence models. However, approaches of this class are inherently slow due to one-by-one token generation, so non-autoregressive alternatives are needed. In this work, we prop…

Cited by 8Source ↗PDF ↗code ↗Scholar ↗
2023

Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts

Eduard Tulchinskii, Kristian Kuznetsov, Kushnareva Laida, Daniil Cherniavskii, Sergey Nikolenko, Evgeny Burnaev +2
NeurIPS 2023poster

Rapidly increasing quality of AI-generated content makes it difficult to distinguish between human and AI-generated texts, which may lead to undesirable consequences for society. Therefore, it becomes increasingly important to study the properties of human texts that are invariant over text domains…

Cited by 82Source ↗PDF ↗code ↗Scholar ↗
2022

Acceptability Judgements via Examining the Topology of Attention Maps

Daniil Cherniavskii, Eduard Tulchinskii, Vladislav Mikhailov, Irina Proskurina, Laida Kushnareva, Ekaterina Artemova +4
EMNLP 2022finding

The role of the attention mechanism in encoding linguistic knowledge has received special interest in NLP. However, the ability of the attention heads to judge the grammatical acceptability of a sentence has been underexplored. This paper approaches the paradigm of acceptability judgments with topol…

Cited by 24Source ↗PDF ↗code ↗Scholar ↗
2021

Artificial Text Detection via Examining the Topology of Attention Maps

Laida Kushnareva, Daniil Cherniavskii, Vladislav Mikhailov, Ekaterina Artemova, Serguei Barannikov, Alexander Bernstein +3
EMNLP 2021main

The impressive capabilities of recent generative models to create texts that are challenging to distinguish from the human-written ones can be misused for generating fake news, product reviews, and even abusive content. Despite the prominent performance of existing methods for artificial text detect…

Cited by 56Source ↗PDF ↗code ↗Scholar ↗
2021

Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detection

Alexander Podolskiy, Dmitry Lipin, Andrey Bout, Ekaterina Artemova, Irina Piontkovskaya
AAAI 2021technical

Real-life applications, heavily relying on machine learning, such as dialog systems, demand for out-of-domain detection methods. Intent classification models should be equipped with a mechanism to distinguish seen intents from unseen ones so that the dialog agent is capable of rejecting the latter a…

Cited by 84Source ↗PDF ↗code ↗Scholar ↗
2020

SumTitles: a Summarization Dataset with Low Extractiveness

Valentin Malykh, Konstantin Chernis, Ekaterina Artemova, Irina Piontkovskaya
COLING 2020main

The existing dialogue summarization corpora are significantly extractive. We introduce a methodology for dataset extractiveness evaluation and present a new low-extractive corpus of movie dialogues for abstractive text summarization along with baseline evaluation. The corpus contains 153k dialogues…

Cited by 9Source ↗PDF ↗code ↗Scholar ↗
2018

Distributed Fine-tuning of Language Models on Private Data

Vadim Popov, Mikhail Kudinov, Irina Piontkovskaya, Petr Vytovtov, Alex Nevidomsky
ICLR 2018poster

One of the big challenges in machine learning applications is that training data can be different from the real-world data faced by the algorithm. In language modeling, users’ language (e.g. in private messaging) could change in a year and be completely different from what we observe in publicly ava…

Cited by 22Source ↗PDF ↗Scholar ↗