Designing an Accurate Reading Skills Test: Why Parallel Texts are Important in Dyslexia Diagnosis
Researchers from the HSE Centre for Language and Brain have developed a tool for accurately assessing reading skills in adults with reading impairments. It can be used, for instance, before and after sessions with a language therapist. The tool includes two texts that differ in content but are equal in complexity: participants were observed to read them at the same speed, make a similar number of errors, and understand the content to the same degree. Such parallel texts will enable more accurate diagnosis of dyslexia and better monitoring of the effectiveness of interventions aimed at addressing it. The paper has been published in Educational Studies.
Reading is a fundamental skill essential for learning, working, and navigating the world. However, even adults may struggle to read at a typical pace, with letters seeming to jump around and word meanings slipping away—leading to frustration and fatigue. Such symptoms are often overlooked, but they may signal dyslexia—a specific reading disorder that begins in childhood and can persist into adulthood without proper intervention, despite normal intelligence, good education, and no vision or hearing impairments.
Accurately diagnosing dyslexia in adults remains a challenge in Russia—one specialist may identify the disorder, another may disagree, and yet another may detect additional issues in the same patient. This inconsistency stems not from a lack of professional expertise but from differences in diagnostic approaches and tools—and more broadly, from the absence of standardised assessment tools for reading skills in Russian-speaking adults.
As a result, without a reliable diagnosis, it is difficult to objectively evaluate the effectiveness of interventions—typically measured by administering a reading test before and after the treatment. However, using the same text before and after an intervention risks the patient memorising it, while using a different text with unknown properties makes it unclear whether any change in reading performance reflects the intervention or merely variation in text complexity.
To address this problem, researchers from the HSE Centre for Language and Brain developed and tested two texts that differ in content but show no significant differences in key linguistic features, such as word length and frequency, sentence syntactic structure, readability according to the Flesch Reading Ease score, and other factors. The researchers hypothesised that these texts would be equally complex for adult native Russian speakers. The final versions were tested on a sample of 111 students.
Yana Kokoreva
'We composed the texts manually, without using neural networks—carefully monitoring sentence syntax, word length, and frequency, while striving to create coherent and meaningful stories. This would not have been possible without the tools provided by our colleagues: we relied on the StimulStat lexical database and the Textometr text complexity analyser, which enabled us to precisely control the psycholinguistic parameters of the texts,' comments co-author Yana Kokoreva, Research Assistant at the HSE Centre for Language and Brain.
The results confirm that both texts can be read with no statistically significant differences in speed, accuracy, or comprehension. This means they can be used to assess reading skills before and after dyslexia interventions, allowing for informed conclusions about their effectiveness. Building on the original paper-based test, the team at HSE’s Centre for Language and Brain has developed a digital version, now available for download.
Svetlana Dorofeeva
'The test can now be used both to diagnose dyslexia in adults and to assess progress following remedial sessions. Our study confirmed that these linguistically validated parallel texts are indeed equally challenging for readers. This means the methodology can be scaled up, allowing new texts to be created for repeated testing of adult readers based on established parameters. The same principles can be applied to develop reading tests for children, provided the parameters are adapted to their age,' says co-author Svetlana Dorofeeva, Research Fellow at the Centre for Language and Brain.
The study was conducted with support from HSE University's Basic Research Programme within the framework of the Centres of Excellence project.
See also:
Neural Network Maps as a Method for Constructing Mathematical Models
Scientists from HSE University–Nizhny Novgorod and the Institute of Physics Belgrade, Serbia, are jointly exploring the application of machine learning techniques and neural networks to the study of nonlinear dynamics. Natalya Stankevich, Leading Research Fellow at the Laboratory of Topological Methods in Dynamics of the Faculty of Informatics, Mathematics, and Computer Science at HSE University–Nizhny Novgorod, spoke to the HSE News Service about this international project.
HSE Scientists Develop Method to Compress Large Language Models Without Losing Quality
Researchers from the AI and Digital Science Institute at the HSE Faculty of Computer Science have developed a new compression method for large language models such as GPT and LLaMA that reduces their size by 25–36% without additional training or significant loss of accuracy. This is the first approach to use mathematical transformations—specifically, rotations of model weights—to make models more amenable to compression with structured matrices. The study results have been published in ACL Findings 2025. The code is available on GitHub.
Machine Learning Models Can Help Reduce Volatility and Boost Stock Market Returns
The use of machine learning models makes it possible to achieve greater accuracy in predicting risks in the Russian stock market compared to classical econometric approaches. The predictive power of these models increases by 23%, while the average investor’s return can reach up to 13% per annum. These conclusions were drawn by Nikita Lysenok from the Department of Financial Market Infrastructure at the HSE Faculty of Economic Sciences. The paper has been published in Fundamental and Applied Mathematics.
Pocket Money, Personal Interest, and Family Practices: What Shapes Students’ Economic Literacy?
University students' economic literacy depends not only on their field of study but also on their interest in economics, the learning environment, and family financial practices. For example, students who received pocket money irregularly tend to perform better on economic literacy tests than their peers who received financial support on a regular basis. These findings come from a study conducted by HSE University involving more than 1,100 students from five Russian universities. The findings have been published in Cakrawala Pendidikan.
Creative Work as a Remedy for Burnout
The creative, supportive atmosphere and innovative methods at the Centre for Sociocultural Research make it appealing to early-career scholars. Over years of working at HSE University, they grow into researchers and lecturers recognised both in Russia and abroad. Chief Research Fellow Zarina Lepshokova and Leading Research Fellow Ekaterina Bushina spoke about their journey at the centre and at HSE, their research, and the role of mentors in their academic success.
HSE Study Reveals Imbalance in the Generative AI Market
Researchers at HSE University analysed how effectively the global generative artificial intelligence market converts investment into real revenue, concluding that AI is currently developing faster than it is paying off. The results have been published in the journal Foresight and STI Governance.
‘Entering Robotics Now Means Growing with the Area’
Unmanned vehicles, courier robots, and smart speakers are rapidly becoming a part of our lives. In 2026, the HSE Faculty of Computer Science opens its new Bachelor’s Programme ‘Design of Intelligent Robotic Systems’ (DIRS). It will train specialists at the intersection of IT, artificial intelligence, and robotics. Academic Supervisor of DIRS Vadim Morgachev explains how studies are organised and why graduates of the programme ‘will definitely be accepted into the future.’
HSE Scientists Train Neural Network to 'Hear' Faults in Electric Motors
Researchers at the AI and Digital Science Institute of the HSE Faculty of Computer Science have developed a new method—the Signature-Guided Data Augmentation (SGDA) framework—that achieves 99% accuracy in motor fault detection and 86% accuracy in fault classification. The application of this approach can reduce industrial equipment repair costs, minimise downtime, and improve production safety. The study results have been published in Engineering Applications of Artificial Intelligence.
MIEM Tech Day at Pokrovka: Exploring HSE’s Engineering DNA Together
On May 26, 2026, the central atrium of the building at 11 Pokrovsky Bulvar will host the annual large-scale festival of engineering developments created by project teams from the HSE Tikhonov Moscow Institute of Electronics and Mathematics (HSE MIEM). The programme includes presentations of the best student technological projects, stands from partner companies and joint workshops, a lecture series featuring practising engineers, a round table on the development of engineering education, and presentations of MIEM master’s degree programmes.
The 'Second Shift' Is Not Why Women Avoid News
Women are more likely than men to avoid political and economic news, but the reasons for this behaviour are linked less to structural inequality or family-related stress than to personal attitudes and the emotional perception of news content. This conclusion was reached by HSE researchers after analysing data from a large-scale survey of more than 10,000 residents across 61 regions of Russia. The study findings have been published in Woman in Russian Society.