Modelling GDPR-Compliant Explanations for Trustworthy AI

Sovrano, Francesco; Vitali, Fabio; Palmirani, Monica

doi:10.1007/978-3-030-58957-8_16

Cited by 13 publications

(12 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed solution builds over the extraction and structuration of an Explanatory Space (ES), intended (as in [28]) as the set of all possible explanations (about an explanandum) reachable by a user, through an explanatory process, starting from an initial explanans, via a pre-defined set of actions. According to the model of Sovrano et al, we might see the ES as a graph of interconnected bits of explanation, and an explanation as nothing more than a path within the ES.…”

Section: Proposed Solutionmentioning

confidence: 99%

From Philosophy to Interfaces: an Explanatory Method and a Tool Inspired by Achinstein’s Theory of Explanation

Sovrano

Vitali

2021

26th International Conference on Intelligent User Interfaces

Self Cite

View full text Add to dashboard Cite

We propose a new method for explanations in Artificial Intelligence (AI) and a tool to test its expressive power within a user interface. In order to bridge the gap between philosophy and humancomputer interfaces, we show a new approach for the generation of interactive explanations based on a sophisticated pipeline of AI algorithms for structuring natural language documents into knowledge graphs, answering questions effectively and satisfactorily. Among the mainstream philosophical theories of explanation we identified one that in our view is more easily applicable as a practical model for user-centric tools: Achinstein's Theory of Explanation. With this work we aim to prove that the theory proposed by Achinstein can be actually adapted for being implemented into a concrete software application, as an interactive process answering questions. To this end we found a way to handle the generic (archetypal) questions that implicitly characterise an explanatory processes as preliminary overviews rather than as answers to explicit questions, as commonly understood. To show the expressive power of this approach we designed and implemented a pipeline of AI algorithms for the generation of interactive explanations under the form of overviews, focusing on this aspect of explanations rather than on existing interfaces and presentation logic layers for question answering. Accordingly, through the identification of a minimal set of archetypal questions it is possible to create a generator of explanatory overviews that is generic enough to significantly ease the acquisition of knowledge by humans, regardless of the specificities of the users outside of a minimum set of very broad requirements (e.g. people able to read and understand English and capable of performing basic common-sense reasoning). We tested our hypothesis on a well-known XAI-powered credit approval system by IBM, comparing CEM, a static explanatory tool for post-hoc explanations, with an extension we developed adding interactive explanations based on our model. The results of the user study, involving more than 100 participants, showed that our proposed solution produced a statistically relevant improvement on effectiveness (U=931.0, p=0.036) over the baseline, thus giving evidence in favour of our theory.

show abstract

Section: Proposed Solutionmentioning

confidence: 99%

From Philosophy to Interfaces: an Explanatory Method and a Tool Inspired by Achinstein’s Theory of Explanation

Sovrano

Vitali

2021

26th International Conference on Intelligent User Interfaces

Self Cite

View full text Add to dashboard Cite

show abstract

“…Additionally, the recent White Paper on Artificial Intelligence [10] emitted by the European Commission stressed the need to monitor and audit not only the Automated Decision-Making system (ADM) algorithms but also the data records used for training, developing, running, the AI systems in order to fight the opacity and to improve transparency. From a technical point of view, there are technologyspecific information to consider in order to fully meet the explanation requirements of the GDPR, for a more detailed overview refer to [35]. The qualities of explanations are listed in different works [25], but the EU Parliament [31] lists the following as a good summary of the current state of the art: intelligibility, understandability, fidelity, accuracy, precision, level of detail, completeness, consistency.…”

Section: Background: the Right To Explanationmentioning

confidence: 99%

“…Thus, in order to answer our research question, what we need is to design a process to effectively allow users to extract explanatory narratives from an Explanatory Space. In [35] we present our model of Explanatory Narrative Process making specific references to the GDPR and the AI-HLEG guidelines, modelling a generic explanatory process, giving a formal definition of explanandum, explanans and Explanatory Space. Hereafter we show a plausible example of YAI in action.…”

Section: Proposed Solutionmentioning

confidence: 99%

Making Things Explainable vs Explaining: Requirements and Challenges under the GDPR

Sovrano,

Vitali,

Palmirani

2021

Preprint

Self Cite

View full text Add to dashboard Cite

The European Union (EU) through the High-Level Expert Group on Artificial Intelligence (AI-HLEG) and the General Data Protection Regulation (GDPR) has recently posed an interesting challenge to the eXplainable AI (XAI) community, by demanding a more user-centred approach to explain Automated Decision-Making systems (ADMs). Looking at the relevant literature, XAI is currently focused on producing explainable software and explanations that generally follow an approach we could term One-Size-Fits-All, that is unable to meet a requirement of centring on user needs. One of the causes of this limit is the belief that making things explainable alone is enough to have pragmatic explanations. Thus, insisting on a clear separation between explainabilty (something that can be explained) and explanations, we point to explanatorY AI (YAI) as an alternative and more powerful approach to win the AI-HLEG challenge. YAI builds over XAI with the goal to collect and organize explainable information, articulating it into something we called user-centred explanatory discourses. Through the use of explanatory discourses/narratives we represent the problem of generating explanations for Automated Decision-Making systems (ADMs) into the identification of an appropriate path over an explanatory space, allowing explainees to interactively explore it and produce the explanation best suited to their needs.

show abstract

“…In fact, we might see the space of all the explanations about an explanandum (or Explanatory Space [33]) as a sort of manifold space where every point within it is interconnected explainable information that is not user-centred locally (because it is the same for every user), but globally as an element of a sequence of information that can be chosen by users according to their interest drifts while exploring the space.…”

Section: Proof Of Concept: An Algorithm For Generating Explanationsmentioning

confidence: 99%

“…Hence, we designed a novel pipeline of AI algorithms for the generation of pragmatic explanations through the extraction and structuration of an Explanatory Space (ES) [33], intended as all the possible explanations (about an explanandum) reachable by a user through an explanatory process, via a pre-defined set of actions, i.e. Open Question Answering and Overviewing.…”

Section: Introductionmentioning

confidence: 99%

Generating User-Centred Explanations via Illocutionary Question Answering: From Philosophy to Interfaces

Sovrano,

Vitali

2021

Preprint

Self Cite

View full text Add to dashboard Cite

We propose a new method for generating explanations with Artificial Intelligence (AI) and a tool to test its expressive power within a user interface. In order to bridge the gap between philosophy and human-computer interfaces, we show a new approach for the generation of interactive explanations based on a sophisticated pipeline of AI algorithms for structuring natural language documents into knowledge graphs, answering questions effectively and satisfactorily. With this work we aim to prove that the philosophical theory of explanations presented by Achinstein can be actually adapted for being implemented into a concrete software application, as an interactive and illocutionary process of answering questions. Specifically, our contribution is an approach to frame illocution in a computer-friendly way, to achieve user-centrality with statistical question answering. In fact, we frame illocution, in an explanatory process, as that mechanism responsible for anticipating the needs of the explainee in the form of unposed, implicit, archetypal questions, hence improving the user-centrality of the underlying explanatory process. More precisely, we hypothesise that given an arbitrary explanatory process, increasing its goal-orientedness and degree of illocution results in the generation of more usable (as per ISO 9241-210) explanations. We tested our hypotheses with a user-study involving more than 60 participants, on two XAI-based systems, one for credit approval (finance) and one for heart disease prediction (healthcare). The results showed that our proposed solution produced a statistically significant improvement (hence with a p-value lower than 0.05) on effectiveness. This, combined with a visible alignment between the increments in effectiveness and satisfaction, suggests that our understanding of illocution can be correct, giving evidence in favour of our theory.CCS Concepts: • Human-centered computing → HCI theory, concepts and models; Empirical studies in HCI.

show abstract

Modelling GDPR-Compliant Explanations for Trustworthy AI

Cited by 13 publications

References 21 publications

From Philosophy to Interfaces: an Explanatory Method and a Tool Inspired by Achinstein’s Theory of Explanation

From Philosophy to Interfaces: an Explanatory Method and a Tool Inspired by Achinstein’s Theory of Explanation

Making Things Explainable vs Explaining: Requirements and Challenges under the GDPR

Generating User-Centred Explanations via Illocutionary Question Answering: From Philosophy to Interfaces

Contact Info

Product

Resources

About