{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T23:36:10Z","timestamp":1783726570682,"version":"3.55.0"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9]]},"abstract":"<jats:p>A large class of Neural-Symbolic (NeSy) methods employs a machine learner to process the input entities, while relying on a reasoner based on First-Order Logic to represent and process more complex relationships among the entities. A fundamental role for these methods is played by the process of logic grounding, which determines the relevant substitutions for the logic rules using a (sub)set of entities.\n\nSome NeSy methods use an exhaustive derivation of all possible substitutions, preserving the full expressive power of the logic knowledge, but leading to a combinatorial explosion of the number of ground formulas to consider and, therefore, strongly limiting their scalability. Other methods rely on heuristic-based selective derivations, which are generally more computationally efficient, but lack a justification and provide no guarantees of preserving the information provided to and returned by the reasoner. \n\nTaking inspiration from multi-hop symbolic reasoning, this paper proposes a parametrized family of grounding methods generalizing classic Backward Chaining. Different selections within this family allow to obtain commonly employed grounding methods as special cases, and to control the trade-off between expressiveness and scalability of the reasoner.\n\nThe experimental results show that the selection of the grounding criterion is often as important as the NeSy method itself.<\/jats:p>","DOI":"10.24963\/ijcai.2025\/535","type":"proceedings-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:10:40Z","timestamp":1758269440000},"page":"4806-4814","source":"Crossref","is-referenced-by-count":1,"title":["Grounding Methods for Neural-Symbolic AI"],"prefix":"10.24963","author":[{"given":"Rodrigo","family":"Castellano Ontiveros","sequence":"first","affiliation":[{"name":"University of Siena"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesco","family":"Giannini","sequence":"additional","affiliation":[{"name":"Scuola Normale Superiore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Gori","sequence":"additional","affiliation":[{"name":"University of Siena"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giuseppe","family":"Marra","sequence":"additional","affiliation":[{"name":"KU Leuven"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michelangelo","family":"Diligenti","sequence":"additional","affiliation":[{"name":"University of Siena"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10584","event":{"name":"Thirty-Fourth International Joint Conference on Artificial Intelligence {IJCAI-25}","theme":"Artificial Intelligence","location":"Montreal, Canada","acronym":"IJCAI-2025","number":"34","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2025,8,16]]},"end":{"date-parts":[[2025,8,22]]}},"container-title":["Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T11:34:18Z","timestamp":1758627258000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2025\/535"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2025\/535","relation":{},"subject":[],"published":{"date-parts":[[2025,9]]}}}