Enabling Ethical AI: A case study in using Ontological Context for Justified Agentic AI Decisions
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915653887197184 |
|---|---|
| author | McGee, Liam Harvey, James Cull, Lucy Vermeulen, Andreas Visscher, Bart-Floris Sharan, Malvika |
| author_facet | McGee, Liam Harvey, James Cull, Lucy Vermeulen, Andreas Visscher, Bart-Floris Sharan, Malvika |
| contents | In this preprint, we present A collaborative human-AI approach to building an inspectable semantic layer for Agentic AI. AI agents first propose candidate knowledge structures from diverse data sources; domain experts then validate, correct, and extend these structures, with their feedback used to improve subsequent models. Authors show how this process captures tacit institutional knowledge, improves response quality and efficiency, and mitigates institutional amnesia. We argue for a shift from post-hoc explanation to justifiable Agentic AI, where decisions are grounded in explicit, inspectable evidence and reasoning accessible to both experts and non-specialists. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_04822 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enabling Ethical AI: A case study in using Ontological Context for Justified Agentic AI Decisions McGee, Liam Harvey, James Cull, Lucy Vermeulen, Andreas Visscher, Bart-Floris Sharan, Malvika Artificial Intelligence In this preprint, we present A collaborative human-AI approach to building an inspectable semantic layer for Agentic AI. AI agents first propose candidate knowledge structures from diverse data sources; domain experts then validate, correct, and extend these structures, with their feedback used to improve subsequent models. Authors show how this process captures tacit institutional knowledge, improves response quality and efficiency, and mitigates institutional amnesia. We argue for a shift from post-hoc explanation to justifiable Agentic AI, where decisions are grounded in explicit, inspectable evidence and reasoning accessible to both experts and non-specialists. |
| title | Enabling Ethical AI: A case study in using Ontological Context for Justified Agentic AI Decisions |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2512.04822 |