Explainable Distributed Case-Based Support Systems: Patterns for Enhancement and Validation of Design Recommendations

Eisenstadt, Viktor; Espinoza-Stapelfeld, Christian; Mikyas, Ada; Althoff, Klaus-Dieter

doi:10.1007/978-3-030-01081-2_6

“…the proportion of AI participating in a joint decision with us. This aspect is especially important in the light of the new tendency toward distributed AI, when the interaction of a large number of AI units is be more the standard than the exception [40]. The model utilized here has the potential to forecast the likely outcome in opinion formation (such as whether a patient should be operated on or not) for a certain proportion of AI or Human agents as they interact.…”

Section: Conclusion and Outlooksmentioning

confidence: 99%

Human-AI ecosystem with abrupt changes as a function of the composition

Contucci¹,

Kertész²,

Osabutey³

2022

Preprint

0

View full text Add to dashboard Cite

The progressive advent of artificial intelligence machines may represent both an opportunity or a threat. In order to have an idea of what is coming we propose a model that simulate a Human-AI ecosystem. In particular we consider systems where agents present biases, peer-to-peer interactions and also three body interactions that are crucial and describe two humans interacting with an artificial agent and two artificial intelligence agents interacting with a human. We focus our analysis by exploring how the relative fraction of artificial intelligence agents affect that ecosystem. We find evidence that for suitable values of the interaction parameters, arbitrarily small changes in such percentage may trigger dramatic changes for the system that can be either in one of the two polarised states or in an undecided state.

show abstract

“…the proportion of AI participating in a joint decision with us. This aspect is especially important in the light of the new tendency toward distributed AI, when the interaction of a large number of AI units is be more the standard than the exception [41]. The model utilized here has the potential to forecast the likely outcome in opinion formation (such as whether a patient should be operated on or not) for a certain proportion of AI or Human agents as they interact.…”

Section: Plos Onementioning

confidence: 99%

Human-AI ecosystem with abrupt changes as a function of the composition

Contucci

¹

,

Kertész

²

,

Osabutey

³

2022

PLoS ONE

6

0

View full text Add to dashboard Cite

The progressive advent of artificial intelligence machines may represent both an opportunity or a threat. In order to have an idea of what is coming we propose a model that simulate a Human-AI ecosystem. In particular we consider systems where agents present biases, peer-to-peer interactions and also three body interactions that are crucial and describe two humans interacting with an artificial agent and two artificial intelligence agents interacting with a human. We focus our analysis by exploring how the relative fraction of artificial intelligence agents affect that ecosystem. We find evidence that for suitable values of the interaction parameters, arbitrarily small changes in such percentage may trigger dramatic changes for the system that can be either in one of the two polarised states or in an undecided state.

show abstract

“…• Explain applies explanation pattern-based methods for (contextual) explanation of retrieval results achieved during the execution of the Find step. The main goal of Explain is to build trust between the user and the system by justifying the returned search results and make the system behavior during the search more transparent (Eisenstadt et al 2018). • Adapt generates variations of the current room configuration and shows how it can evolve in the future.…”

Section: Introductionmentioning

confidence: 99%