We are proud to announce that Syed Juned Ali, Zhuoxun Zheng, and Dominik Bork from the Business Informatics Group received the Best Paper Award at the 38th International Conference on Advanced Information Systems Engineering (CAiSE 2026) for their paper "Shortcut or Understanding? Diagnosing LLM Type Prediction in Conceptual Models."

The paper investigates how natural language labels and structural context influence the accuracy of automated type prediction in conceptual models across different AI paradigms. The findings show that meaningful natural language semantics are the primary driver of predictive performance, while structural cues provide complementary support mainly when labels are incomplete—highlighting the need for future architectures that go beyond surface-level lexical shortcuts toward genuine structural reasoning.

Congratulations to the authors on this outstanding recognition!

Read the full announcement