In this post, we present a straightforward yet revealing task: classifying 25 philosophical and scientific arguments as either deductive or inductive. We tested Mistral Le Chat on this argument classification task to evaluate its ability to distinguish between these fundamental forms of reasoning. Le Chat demonstrated a solid grasp of
Can a language model accurately classify argumentative claims without any prior examples or fine-tuning? We put DeepSeek-V3 to the test on a real-world stance classification task involving 200 claims from a structured dataset. The model was asked to determine, for each claim, whether it supported (PRO) or opposed (CON) a
Natural Language Processing (NLP) allows us to automatically analyse and categorise textual data. With the help of GenAI, even complex classification tasks can now be executed using just a well-designed prompt. In this post, we present a practical example where GenAI classifies financial-related sentences into domain-specific categories, showcasing how effective
Recent advances in Generative AI offer researchers new opportunities to assign topic labels to political and legislative texts without manual coding or programming. The Comparative Agendas Project (CAP) provides a structured topic classification system that captures the major areas of public policy. Traditionally, applying these labels required manual annotation or
Classifying gender based on names might initially appear straightforward, yet different AI models vary significantly in how accurately and effectively they handle this task. This blog explores the performance of various models when provided with a structured prompt for name-based gender classification using an uploaded .xlsx file. The evaluation specifically
