CompoST: A Benchmark for Analyzing the Ability of LLMs to Compositionally Interpret Questions in a QALD Setting

David Maria Schmidt, Raoul Schubert, Philipp Cimiano. CompoST: A Benchmark for Analyzing the Ability of LLMs to Compositionally Interpret Questions in a QALD Setting. In Daniel Garijo, Sabrina Kirrane, Angelo A. Salatino, Cogan Shimizu, Maribel Acosta, Andrea Giovanni Nuzzolese, Sebastián Ferrada, Thibaut Soulard, Kouji Kozaki, Hideaki Takeda 0001, Anna Lisa Gentile, editors, The Semantic Web - ISWC 2025 - 24th International Semantic Web Conference, Nara, Japan, November 2-6, 2025, Proceedings, Part I. Volume 16140 of Lecture Notes in Computer Science, pages 3-22, Springer, 2025. [doi]

Authors

David Maria Schmidt

This author has not been identified. Look up 'David Maria Schmidt' in Google

Raoul Schubert

This author has not been identified. Look up 'Raoul Schubert' in Google

Philipp Cimiano

This author has not been identified. It may be one of the following persons: Look up 'Philipp Cimiano' in Google