@inproceedings{ManGiaAli-24-IJCLR-IC,
author = {Manhaeve, Robin
and Giannini, Francesco
and Ali, Mehdi
and Azzolini, Damiano
and Bizzarri, Alice
and Borghesi, Andrea
and Bortolotti, Samuele
and De Raedt, Luc
and Dhami, Devendra
and Diligenti, Michelangelo
and Duman{\v{c}}i{\'{c}}, Sebastijan
and Faltings, Boi
and Gentili, Elisabetta
and Gerevini, Alfonso
and Gori, Marco
and Guns, Tias
and Homola, Martin
and Kersting, Kristian
and Lehmann, Jens
and Lombardi, Michele
and Lorello, Luca
and Marconato, Emanuele
and Melacci, Stefano
and Passerini, Andrea
and Paul, Debjit
and Riguzzi, Fabrizio
and Teso, Stefano
and Yorke-Smith, Neil
and Lippi, Marco},
editor = {Dai, Wang-Zhou},
title = {Benchmarking in Neuro-Symbolic AI},
booktitle = {Learning and Reasoning: 4th International Joint Conference on Learning and Reasoning, IJCLR 2024, and 33rd International Conference on Inductive Logic Programming, ILP 2024, Nanjing, China, September 20--22, 2024, Proceedings},
year = {2026},
publisher = {Springer Nature Switzerland},
address = {Cham},
pages = {238--249},
abstract = {Neural-symbolic (NeSy) AI has gained a lot of popularity by enhancing learning models with explicit reasoning capabilities. Both new systems and new benchmarks are constantly introduced and used to evaluate learning and reasoning skills. The large variety of systems and benchmarks, however, makes it difficult to establish a fair comparison among the various frameworks, let alone a unifying set of benchmarking criteria. This paper analyzes the state-of-the-art in benchmarking NeSy systems, studies its limitations, and proposes ways to overcome them. We categorize popular neural-symbolic frameworks into three groups: model-theoretic, proof-theoretic fuzzy, and proof-theoretic probabilistic systems. We show how these three categories have distinct strengths and weaknesses, and how this is reflected in the type of tasks and benchmarks to which they are applied.},
doi = {10.1007/978-3-032-09087-4_17},
isbn = {978-3-032-09087-4}
}
This file was generated by bibtex2html 1.98.