• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

AI Assists with Fact-Checking: HSE Scientists Streamline Information Verification

AI Assists with Fact-Checking: HSE Scientists Streamline Information Verification

© iStock

Specialists at the HSE AI Research Centre have developed an AI-powered fact-checking assistant. This software solution will improve the quality of working with information, reduce the risks of errors and biases, and save both time and resources. A notable advantage of the program lies in its capability to process a wide variety of statement types.

Today, neural networks are commonly used for statement verification, even though they were not initially designed for this purpose and may 'hallucinate’, generating texts that do not align with reality. Neural networks are trained on extensive datasets; if these datasets contain errors or inaccuracies, the network's outputs may be erroneous. The fact-checking assistant developed at HSE University aims to address this problem.

The program is made up of several key components, which include searching for text fragments relevant to the user's statement, comparing these fragments with the statement, and, finally, making a conclusive decision regarding the statement's accuracy. The program's outputs include the final decision, the probability of its accuracy, and the text fragments that either corroborate or contradict the statement.

Dmitry Ilvovsky

Dmitry Ilvovsky, head of the project 'AI in Information Processes' at the AI Research Centre, HSE University

'A notable advantage of the program lies in its capability to process various types of statements. Through the use of machine learning and modern algorithms, we have attained a reasonably high level of accuracy and reliability in terms of information processing and analysis. However, using the assistant requires a certain degree of caution, as it cannot fully replace professional fact-checking, and its scope of application is limited.'

The program's customisable algorithm comprises several fairly reliable components that can be further refined and improved. Specifically, the scientists trained the program to run fact checks automatically using data from Wikipedia in Russian, English, and Bulgarian. Technically, the program can handle any statement presented in the form of a text longer than five words. If a specific fact mentioned in the statement is not found in Wikipedia, the program is likely to indicate that there is 'insufficient information' to perform a check. This is one of the standard responses of the system.

The developers at HSE University can customise the program upon request and train it on data from specific sources. The virtual assistant features a user-friendly interface and is suitable for use by researchers, fact-checkers, or framework developers as either an integrated verification tool or a browser plug-in.

Please refer to the HSE AI Research Centre for more details about the product.

See also:

HSE University to Reward Students Who Write Their Thesis Using AI

HSE University has launched a competition for solutions using artificial intelligence technology in theses work. The goal of the competition is to evaluate how students use tools based on generative models in their 2024 graduation theses (GT).

Production of the Future: AI Research Centre Presents Its Developments in Manual Operations Control Systems

Researchers from the HSE AI Research Centre have built a system for the automated control of manual operations, which finds application in industrial production. The system facilitates the process of monitoring objects and actions, as well as controlling the quality of their execution.

HSE and Yandex to Expand Collaboration in Training AI Specialists

Over the next ten years, the partnership between Yandex and the HSE Faculty of Computer Science (FCS) will broaden across three key areas: launching new educational programmes, advancing AI research, and exploring the application of generative neural networks in the educational process. Established by HSE University and Yandex a decade ago, the Faculty of Computer Science has since emerged as a frontrunner in training developers and experts in AI and machine learning, with a total of 3,385 graduates from the faculty over this period.

‘The Goal of the Spring into ML School Is to Unite Young Scientists Engaged in Mathematics of AI’

The AI and Digital Science Institute at the HSE Faculty of Computer Science and Innopolis University organised a week-long programme for students, doctoral students, and young scientists on the application of mathematics in machine learning and artificial intelligence. Fifty participants of Spring into ML attended 24 lectures on machine learning, took part in specific pitch sessions, and completed two mini-courses on diffusion models—a developing area of AI for data generation.

Researchers ‘Personalise’ the Selection of a Neural Network for Face Recognition on Smartphones

Researchers from HSE University in Nizhny Novgorod, MISIS and the Artificial Intelligence Research Institute (AIRI) have developed an algorithm that selects the best available neural network for facial recognition, taking into account the features of a mobile device. This new approach accelerates the selection of the most suitable neural network and allows the identification of people with an accuracy rate of up to 99%. The study was published in the IEEE Access journal. The source code is available on GitHub.

‘Bots Are Simply Imitators, not Artists’: How to Distinguish Artificial Intellect from a Real Author

Today, text bots like ChatGPT are doing many tasks that were originally human work. In our place, they can rewrite ‘War and Peace’ in a Shakespearean style, write a thesis on Ancient Mesopotamia, or create a Valentine’s Day card. But is there any way to identify an AI-generated text and distinguish it from works done by a human being? Can we catch out a robot? The Deputy Head of the HSE School of Data Analysis and Artificial Intelligence, Professor of the HSE Faculty of Computer Science Vasilii Gromov explained the answer in his lecture ‘Catch out a Bot, or the Large-Scale Structure of Natural Intelligence’ for Znanie intellectual society.

Neural Network Developed at HSE Campus in Perm Will Determine Root Cause of Stroke in Patients

Specialists at HSE Campus in Perm and clinicians at Perm City Clinical Hospital No. 4, have been collaborating to develop a neural network capable of determining the root cause of a stroke. This marks the world's first attempt to create such a system, the developers note.

HSE University and Neimark IT Campus Sign an Agreement on Launching an AI Network Programme

HSE University, together with the world-class Neimark IT campus, is preparing a unique professional environment for future IT specialists: to this end, an IT school will be created in the Nizhny Novgorod region, and on September 1st, the first network degree programme ‘Artificial and Augmented Intelligence Technologies’ will be launched at HSE University in Nizhny Novgorod.

Russian Scientists Develop AI Algorithm for Faster Prediction of Earthquakes and Disease Outbreaks

Researchers at the HSE University AI Research Centre and Faculty of Computer Science have proposed a novel algorithm for detecting structural changes in time series. The method uses a neural network to compare various segments of a series, enabling rapid detection of changes in its behaviour. The results of their work have been presented at the 26th International Conference on Artificial Intelligence and Statistics— AISTATS (A*).

Neural Networks of Power: AI Unravels Knots and Tangles in Relationships between Humans, Elves and Hobbits

One of the most popular writers of the last century, John Ronald Reuel Tolkien, was born on January 3rd. Researchers from HSE University, AIRI and MISSIS have used machine learning to explore the social connections between the characters of his Middle-earth universe. The algorithm managed to create an accurate picture of the social structures and dynamics of the characters' relationships, providing a unique map of interactions in the epic world. The results of the work were published in IEEE Xplore.