Accountability of AI Under the Law: The Role of Explanation

Doshi‐Velez, Finale; Kortz, Mason; Budish, Ryan; Bavitz, Chris; Gershman, Sam; O’Brien, D. P.; Scott, Kate M.; Schieber, Stuart; Waldo, James; Weinberger, David; Weller, Adrian; Wood, Alexandra

doi:10.48550/arxiv.1711.01134

Cited by 67 publications

(83 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Further, the principle of accountability is particularly important when considering regulatory conditions. For regulatory bodies standards for accountability in AI remain an open question as they seek a balance between creator responsibility and taking full advantage of the capabilities of AI [13].…”

Section: Accountabilitymentioning

confidence: 99%

Know Your Model (KYM): Increasing Trust in AI and Machine Learning

Roszel,

Norvill,

Hilger

et al. 2021

Preprint

View full text Add to dashboard Cite

The widespread utilization of AI systems has drawn attention to the potential impacts of such systems on society. Of particular concern are the consequences that prediction errors may have on realworld scenarios, and the trust humanity places in AI systems. It is necessary to understand how we can evaluate trustworthiness in AI and how individuals and entities alike can develop trustworthy AI systems. In this paper, we analyze each element of trustworthiness and provide a set of 20 guidelines that can be leveraged to ensure optimal AI functionality while taking into account the greater ethical, technical, and practical impacts to humanity. Moreover, the guidelines help ensure that trustworthiness is provable and can be demonstrated, they are implementation agnostic, and they can be applied to any AI system in any sector.

show abstract

Section: Accountabilitymentioning

confidence: 99%

Know Your Model (KYM): Increasing Trust in AI and Machine Learning

Roszel,

Norvill,

Hilger

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Using such systems in legal applications, however, raises a number of issues [9], including bias, adapting to changes in statute law, case law and social values, and, perhaps most important, the lack of explanation. In law there is a right to explanation [22] and so providing explanations that users can understand is essential if AI systems are to be used in practice. This has long been recognised in AI and Law and the provision of explanations has been a central feature of systems developed in the field [6].…”

Section: Introductionmentioning

confidence: 99%

Using Issues to Explain Legal Decisions

Bench-Capon

2021

Preprint

View full text Add to dashboard Cite

The need to explain the output from Machine Learning systems designed to predict the outcomes of legal cases has led to a renewed interest in the explanations offered by traditional AI and Law systems, especially those using factor based reasoning and precedent cases. In this paper we consider what sort of explanations we should expect from such systems, with a particular focus on the structure that can be provided by the use of issues in cases.

show abstract

“…The latter idea is known as actionable recourse [27,52], and is important for high-stakes decisions such as credit decisioning and healthcare. The European Union now legally stipulates that any individual subject to (semi)-autonomous decision making has the right to an explanation [54,16], and similar rights to explanation have existed in the US in domains such as credit decisioning [11].…”

Section: Introductionmentioning

confidence: 99%

Counterfactual Explanations for Arbitrary Regression Models

Spooner,

Dervovic,

Long

et al. 2021

Preprint

View full text Add to dashboard Cite

We present a new method for counterfactual explanations (CFEs) based on Bayesian optimisation that applies to both classification and regression models. Our method is a globally convergent search algorithm with support for arbitrary regression models and constraints like feature sparsity and actionable recourse, and furthermore can answer multiple counterfactual questions in parallel while learning from previous queries. We formulate CFE search for regression models in a rigorous mathematical framework using differentiable potentials, which resolves robustness issues in threshold-based objectives. We prove that in this framework, (a) verifying the existence of counterfactuals is NP-complete; and (b) that finding instances using such potentials is CLS-complete. We describe a unified algorithm for CFEs using a specialised acquisition function that composes both expected improvement and an exponential-polynomial (EP) family with desirable properties. Our evaluation on real-world benchmark domains demonstrate high sample-efficiency and precision.Preprint. Under review.

show abstract

Accountability of AI Under the Law: The Role of Explanation

Cited by 67 publications

References 0 publications

Know Your Model (KYM): Increasing Trust in AI and Machine Learning

Know Your Model (KYM): Increasing Trust in AI and Machine Learning

Using Issues to Explain Legal Decisions

Counterfactual Explanations for Arbitrary Regression Models

Contact Info

Product

Resources

About