The demand for contrastive explanations

Elzein, Nadine

doi:10.1007/s11098-018-1065-z

Cited by 7 publications

(3 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, they can be employed with the aim of adjusting the contents of the explanation for the algorithm's output in accordance with the user's preferences [46]. Finally, the ability to explain a decision contrastively is claimed to lead to responsible decision-making [47].…”

Section: Contrastive and Counterfactual Explanation In The Contextmentioning

confidence: 99%

A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence

et al. 2021

View full text Add to dashboard Cite

A number of algorithms in the field of artificial intelligence offer poorly interpretable decisions. To disclose the reasoning behind such algorithms, their output can be explained by means of so-called evidence-based (or factual) explanations. Alternatively, contrastive and counterfactual explanations justify why the output of the algorithms is not any different and how it could be changed, respectively. It is of crucial importance to bridge the gap between theoretical approaches to contrastive and counterfactual explanation and the corresponding computational frameworks. In this work we conduct a systematic literature review which provides readers with a thorough and reproducible analysis of the interdisciplinary research field under study. We first examine theoretical foundations of contrastive and counterfactual accounts of explanation. Then, we report the state-of-the-art computational frameworks for contrastive and counterfactual explanation generation. In addition, we analyze how grounded such frameworks are on the insights from the inspected theoretical approaches. As a result, we highlight a variety of properties of the approaches under study and reveal a number of shortcomings thereof. Moreover, we define a taxonomy regarding both theoretical and practical approaches to contrastive and counterfactual explanation.

show abstract

Section: Contrastive and Counterfactual Explanation In The Contextmentioning

confidence: 99%

A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Diverse research argues that contrastive explanations are inherent to human cognition [33,34,35], and thus relevant to XAI. In philosophy, contrastive explanations are claimed to be necessary for moral responsibility [36]. And, furthermore, two of the four types of explanatory questions identified by Van Bouwel and Weber [37] lead to contrastive explanations.…”

Section: Contrastive and Counterfactualmentioning

confidence: 99%

On the Rationality of Explanations in Classification Algorithms

Falomir

Costa

2021

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

This paper is a first step towards studying the rationality of explanations produced by up-to-date AI systems. Based on the thesis that designing rational explanations for accomplishing trustworthy AI is fundamental for ethics in AI, we study the rationality criteria that explanations in classification algorithms have to meet. In this way, we identify, define, and exemplify characteristic criteria of rational explanations in classification algorithms.

show abstract

“…Our approach provides two main contributions. First, we construct explanations for the behavior of an agent governed by temporal logic rules acting in a deterministic relational Markov decision process (RMDP) , including questions about the agent's rules and actions and "why" queries requiring a contrastive explanation (Elzein, 2019) appealing to the temporal logic rules (content generation; section 3). Second, we convert these explanation structures into natural language, constructing natural language clauses from statements belonging to a fragment of our temporal logic, and embedding these into general response templates (surface representation generation; section 4).…”

Section: Introductionmentioning

confidence: 99%

Generating justifications for norm-related agent decisions

Kasenberg¹,

Roque²,

Thielstrom³

et al. 2019

Proceedings of the 12th International Conference on Natural Language Generation

View full text Add to dashboard Cite

We present an approach to generating natural language justifications of decisions derived from norm-based reasoning. Assuming an agent which maximally satisfies a set of rules specified in an object-oriented temporal logic, the user can ask factual questions (about the agent's rules, actions, and the extent to which the agent violated the rules) as well as "why" questions that require the agent comparing actual behavior to counterfactual trajectories with respect to these rules. To produce natural-sounding explanations, we focus on the subproblem of producing natural language clauses from statements in a fragment of temporal logic, and then describe how to embed these clauses into explanatory sentences. We use a human judgment evaluation on a testbed task to compare our approach to variants in terms of intelligibility, mental model and perceived trust.

show abstract

The demand for contrastive explanations

Cited by 7 publications

References 46 publications

A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence

A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence

On the Rationality of Explanations in Classification Algorithms

Generating justifications for norm-related agent decisions

Contact Info

Product

Resources

About