Search by tag «Large Language Models» 2 results

• AI Busted: ITMO Researchers Learn to Detect AI-Modified Texts

  Scientists at ITMO University developed an LLM-based tool that analyzes text content and style to detect whether it was written by a human or an AI. The detector demonstrates the accuracy of 94% and can not only spot AI-generated writings but also offer suggestions to humanize the text. The service will be of use for proper AI labeling, as well as reviewing student papers and corporate documents. A demo version of the technology (in Russian) is already available for testing; we tried it, and it does not lie – this article was indeed written by a real person.

  09.09.2025

• Automate Your Coding with OSA – ITMO-Made AI Assistant for Researchers

  The recently unveiled Open Source Advisor (OSA) is an LLM-based tool that can “tidy up” open-source research code repositories to make them more accessible to other research teams. Developed by the staff of ITMO University, OSA can help replicate experiments or launch algorithms described in publications. By facilitating the systematization of research data, the tool increases the value of scientific papers. OSA will be equally beneficial to coders and to those wishing to make sense of data acquired by other research teams. 

  29.04.2025