HSE University and Sber Researchers to Make AI More Empathetic
Researchers at the HSE AI Research Centre and Sber AI Lab have developed a special system that, using large language models, will make artificial intelligence (AI) more emotional when communicating with a person. Multi-agent models, which are gaining popularity, will be engaged in the synthesis of AI emotions. The article on this conducted research was published as part of the International Joint Conference on Artificial Intelligence (IJCAI) 2024.
The system is based on effective AI models of computer vision developed by the authors for recognising user facial expressions, which can be run directly on their devices. While using these models during a dialogue the emotions of the interlocutor are analysed in real time, including AI responses, which can help in building special datasets for training and improving the system for generating emotional responses to user requests.
One of the article authors, Associate Professor at the Department of Information Systems and Technologies at HSE University in Nizhny Novgorod
‘In our system, the recognised emotion is used to select a more empathic AI response, which is generated simultaneously by several language models tuned to basic emotions: joy, sadness, fear or anger. As a result, the received response contains a more detailed analysis of the recommendations issued by AI, their advantages and disadvantages in terms of the emotional reaction of users to them.’
The HSE University and Sber solution can be applied to situations when it is important to take into account the emotional state of users: in company chatbots, support services, educational applications and other areas where contact with the client is required. As a result, suggestions and recommendations of products and services will look more natural and empathetic. This will allow companies to better communicate with customers, give researchers a new tool for exploring emotions, and let users interact with AI more effectively. Today, AI models have already been applied in the development of GigaPevt, a medical diagnostic assistant based on the large GigaChat language model, to analyse the user's emotional state.
See also:
‘HSE’s Industry Ties Are Invaluable’
Pan Zhengwu has spent the last seven years at HSE University—first as a student of the Bachelor’s in Software Engineering and now in the Master’s in System and Software Engineering at the Faculty of Computer Science. In addition to his busy academic schedule, he works as a mobile software engineer at Yandex and is an avid urban photographer. In his interview with the HSE News Service, Zhengwu talks about the challenges he faced when he first moved to Russia, shares his thoughts on ‘collaborating’ with AI, and reveals one of his top spots for taking photos in Moscow.
Scientists Present New Solution to Imbalanced Learning Problem
Specialists at the HSE Faculty of Computer Science and Sber AI Lab have developed a geometric oversampling technique known as Simplicial SMOTE. Tests on various datasets have shown that it significantly improves classification performance. This technique is particularly valuable in scenarios where rare cases are crucial, such as fraud detection or the diagnosis of rare diseases. The study's results are available on ArXiv.org, an open-access archive, and will be presented at the International Conference on Knowledge Discovery and Data Mining (KDD) in summer 2025 in Toronto, Canada.
Megascience, AI, and Supercomputers: HSE Expands Cooperation with JINR
Experts in computer technology from HSE University and the Joint Institute for Nuclear Research (JINR) discussed collaboration and joint projects at a meeting held at the Meshcheryakov Laboratory of Information Technologies (MLIT). HSE University was represented by Lev Shchur, Head of the Laboratory for Computational Physics at the HSE Tikhonov Moscow Institute of Electronics and Mathematics (HSE MIEM), as well as Denis Derkach and Fedor Ratnikov from the Laboratory of Methods for Big Data Analysis at the HSE Faculty of Computer Science.
AI vs AI: Scientists Develop Neural Networks to Detect Generated Text Insertions
A research team, including Alexander Shirnin from HSE University, has developed two models designed to detect AI-generated insertions in scientific texts. The AIpom system integrates two types of models: a decoder and an encoder. The Papilusion system is designed to detect modifications through synonyms and summarisation by neural networks, using one type of models: encoders. In the future, these models will assist in verifying the originality and credibility of scientific publications. Articles describing the Papilusion and AIpom systems have been published in the ACL Anthology Digital Archive.
HSE Researchers Develop Python Library for Analysing Eye Movements
A research team at HSE University has developed EyeFeatures, a Python library for analysing and modelling eye movement data. This tool is designed to simplify the work of scientists and developers by enabling them to efficiently process complex data and create predictive models.
‘Many Want to Create AI-Based Products and Become More Competitive’
In 2024, the online Russian-taught master’s programme ‘Artificial Intelligence,’ offered by the HSE Faculty of Computer Science, saw a record number of first-year students—over 300. What accounts for such a high interest in AI, how the curriculum is structured, and what new skills will graduates acquire? Elena Kantonistova, the programme’s academic director, shares more.
'I Would Like to Leave a Lasting Impact on Science'
Aibek Alanov pursues his own scientific research and leads two teams of scientists, one at HSE University and the other at AIRI. In this interview for the HSE Young Scientists project, he explores the parallels between today's AI researchers and early 20th-century physicists, discusses generative models, and shares his passion for bachata partner dancing.
HSE’S Achievements in AI Presented at AIJ
The AI Journey international conference hosted a session led by Deputy Prime Minister Dmitry Chernyshenko highlighting the achievements of Russian research centres in artificial intelligence. Alexey Masyutin, Head of the HSE AI Research Centre, showcased the centre’s key developments.
Drivers of Progress and Sources of Revenue: The Role of Universities in Technology Transfer
In the modern world, the effective transfer of socio-economic and humanities-based knowledge to the real economy and public administration is essential. Universities play a decisive role in this process. They have the capability to unite diverse teams and, in partnership with the state and businesses, develop and enhance advanced technologies.
AI on Guard of Ecology: Students from Russia and Belarus Propose New Solutions to Environmental Problems
An international online hackathon dedicated to solving environmental problems was held at HSE University in Nizhny Novgorod. Students employed artificial intelligence and computer vision to develop innovative solutions for image segmentation, predictive modelling (forecasting future events based on data from the past) of emissions and creating chatbots for nature reserves and national parks.