Managed and organized a study project focused on “Supporting the Review Process with AI” - an AI-driven system developed by master’s students to assist with the academic reviewing process.
Our AI-driven system automates source validation by verifying the accuracy of citations against their original sources and facilitates literature discovery by identifying relevant scientific papers for a given topic. Additionally, the system aims to make the argument structure easier to digest and analyze by turning the contents of the paper into a graph database. This project aims to streamline the review process, enhance citation accuracy, and support high-quality academic work through practical AI applications.
The system extracts references from uploaded research papers and automatically retrieves the original sources. Using AI-based text analysis, it evaluates how accurately and contextually correct the sources are cited. This ensures citation integrity, reduces the risk of misrepresentation, and provides structured feedback to enhance academic precision.
The system transforms the content of research papers into a graph database, representing the relationships between different concepts, arguments, and evidence. This visualization aids in understanding complex arguments and facilitates deeper analysis, making it easier for reviewers to navigate through the paper’s structure and logic.
Given a scientific topic, the system searches across multiple academic databases to identify high-quality and relevant research papers. The AI ranks sources based on credibility, relevance, and recent advancements, helping researchers efficiently find the most suitable literature for their work.
