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

Abstract

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.

An Objective Metric for Explainable AI: How and Why to Estimate the Degree of Explainability

“…Notwithstanding this definition, illocution seems to be too abstract to be implementable into a concrete software. Nonetheless, recent efforts towards the automated generation of explanations (Sovrano & Vitali, 2021), have shown that it may be possible to define illocution in a more "computer-friendly" way. As stated by Sovrano and Vitali, illocution in explaining involves informed and pertinent answers not just to the main question, but also to other questions of various kinds, even unrelated to causality, that are relevant to the explanations.…”

“…For estimating pertinence, plain Question Answering is probably the easiest approach to implement or fine-tune, being fully end-to-end, but it may be computationally unfeasible for computing the DoX of large-enough information and amounts of Explanandum Aspects. Therefore, an approach like the one used by Sovrano & Vitali, 2021, for archetypal question answering, is more suitable to our ends, allowing for both the identification of details (or information units) and the estimation of pertinence.…”

“…The credit approval system is the same used also in Sovrano & Vitali, 2021, designed by IBM to showcase its XAI library: AIX360. This explanandum is about finance and the system is used by a bank.…”

“…We assert that it is possible to quantify the Degree of eXplainability (DoX) of a dataset by applying the Achinstein-based definition of explanation proposed in Sovrano & Vitali, 2021. Thus, drawing also from Carnap's criteria of adequacy of an explanation (Novaes & Reck, 2017), we frame the DoX as the average Explanatory Illocution of information on the Explanandum As-pects 2 .…”

Agree to Disagree: Subjective Fairness in Privacy-Restricted Decentralised Conflict Resolution

“…As the gap between objective and subjective fairness resides on the need for reasoning and justification, explanations ( Čyras et al, 2019 ; Rosenfeld and Richardson, 2019 ; Sovrano and Vitali, 2021 ) artlessly lend themselves as desirable tools to address this issue. This is the focus of much of prior literature concerning explanations to human users.…”