We present a multi-modal Logic for Functional Responsibility (LFR) to model and check actual, capacity, and outcome responsibility of agents within hybrid computational systems with a user level ontology. For AI systems, this allows one to represent and trace responsibility of output to training data, training engine, trained model, policies and end user operations. We exemplify the system with an example of image generation.
Formalising Functional Responsibility in Hybrid Multi-agent Systems / A.G. Buda, G.P. (LECTURE NOTES IN COMPUTER SCIENCE). - In: Multi-Agent Systems. EUMAS 2026 / [a cura di] F. Lorig, P. Davidsson, F. Klügl, V. Camps, J.C. Nieves Sanchez, E. Kaddoum. - [s.l] : Springer Nature, 2026. - ISBN 9783032393944. - pp. 459-476 (( 23. EUMAS Malmö 2026 [10.1007/978-3-032-39395-1_26].
Formalising Functional Responsibility in Hybrid Multi-agent Systems
G. Primiero
2026
Abstract
We present a multi-modal Logic for Functional Responsibility (LFR) to model and check actual, capacity, and outcome responsibility of agents within hybrid computational systems with a user level ontology. For AI systems, this allows one to represent and trace responsibility of output to training data, training engine, trained model, policies and end user operations. We exemplify the system with an example of image generation.
| File | Dimensione | Formato | |
|---|---|---|---|
|
978-3-032-39395-1_26.pdf
accesso aperto
Tipologia:
Publisher's version/PDF
Licenza:
Creative commons
Dimensione
1.55 MB
Formato
Adobe PDF
|
1.55 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
