41 citations · 43 across the 4 of their papers we have counts for
4 papers
Taxonomy-Driven Analysis of Open-Source AI Risk Mitigation Tools
Afreen Alam, Evgenija Popchanovska, Ana Gjorgjevikj +4
Rapid adoption of large language models (LLMs) in enterprise settings has introduced operational, security, and governance risks. As generative AI applications move from pilot to p…
When AI Fails, What Works? A Data-Driven Taxonomy of Real-World AI Risk Mitigation Strategies
Evgenija Popchanovska, Ana Gjorgjevikj, Maryan Rizinski +3
Large language models (LLMs) are increasingly embedded in high-stakes workflows, where failures propagate beyond isolated model errors into systemic breakdowns that can lead to leg…
Sentiment Analysis in Finance: From Transformers Back to eXplainable Lexicons (XLex)
Maryan Rizinski, Hristijan Peshov, Kostadin Mishev +2
Lexicon-based sentiment analysis (SA) in finance leverages specialized, manually annotated lexicons created by human experts to extract sentiment from financial texts. Although lex…
Company classification using zero-shot learning
Maryan Rizinski, Andrej Jankov, Vignesh Sankaradas +3
In recent years, natural language processing (NLP) has become increasingly important in a variety of business applications, including sentiment analysis, text classification, and n…