Ensure “Interpretability” of AI systems

Principle: Decisions made by an AI agent should be possible to understand, especially if those decisions have implications for public safety, or result in discriminatory practices. Recommendations: Ensure Human Interpretability of Algorithmic Decisions: AI systems must be designed with the minimum requirement that the designer can account for an AI agent’s behaviors. Some systems with potentially severe implications for public safety should also have the functionality to provide information in the event of an accident. Empower Users: Providers of services that utilize AI need to incorporate the ability for the user to request and receive basic explanations as to why a decision was made.
Principle: Guiding Principles and Recommendations, Apr 18, 2017

Published by Internet Society, "Artificial Intelligence and Machine Learning: Policy Paper"

Related Principles

Transparency and explainability

There should be transparency and responsible disclosure to ensure people know when they are being significantly impacted by an AI system, and can find out when an AI system is engaging with them. This principle aims to ensure responsible disclosure when an AI system is significantly impacting on a person’s life. The definition of the threshold for ‘significant impact’ will depend on the context, impact and application of the AI system in question. Achieving transparency in AI systems through responsible disclosure is important to each stakeholder group for the following reasons for users, what the system is doing and why for creators, including those undertaking the validation and certification of AI, the systems’ processes and input data for those deploying and operating the system, to understand processes and input data for an accident investigator, if accidents occur for regulators in the context of investigations for those in the legal process, to inform evidence and decision‐making for the public, to build confidence in the technology Responsible disclosures should be provided in a timely manner, and provide reasonable justifications for AI systems outcomes. This includes information that helps people understand outcomes, like key factors used in decision making. This principle also aims to ensure people have the ability to find out when an AI system is engaging with them (regardless of the level of impact), and are able to obtain a reasonable disclosure regarding the AI system.

Published by Department of Industry, Innovation and Science, Australian Government in AI Ethics Principles, Nov 7, 2019

1. Principle of proper utilization

Users should make efforts to utilize AI systems or AI services in a proper scope and manner, under the proper assignment of roles between humans and AI systems, or among users. [Main points to discuss] A) Utilization in the proper scope and manner On the basis of the provision of information and explanation from developers, etc. and with consideration of social contexts and circumstances, users may be expected to use AI in the proper scope and manner. In addition, users may be expected to recognize benefits and risks, understand proper uses, acquire necessary knowledge and skills and so on before using AI, according to the characteristics, usage situations, etc. of AI. Furthermore, users may be expected to check regularly whether they use AI in an appropriate scope and manner. B) Proper balance of benefits and risks of AI AI service providers and business users may be expected to take into consideration proper balance between benefits and risks of AI, including the consideration of the active use of AI for productivity and work efficiency improvements, after appropriately assessing risks of AI. C) Updates of AI software and inspections repairs, etc. of AI Through the process of utilization, users may be expected to make efforts to update AI software and perform inspections, repairs, etc. of AI in order to improve the function of AI and to mitigate risks. D) Human Intervention Regarding the judgment made by AI, in cases where it is necessary and possible (e.g., medical care using AI), humans may be expected to make decisions as to whether to use the judgments of AI, how to use it etc. In those cases, what can be considered as criteria for the necessity of human intervention? In the utilization of AI that operates through actuators, etc., in the case where it is planned to shift to human operation under certain conditions, what kind of matters are expected to be paid attention to? [Points of view as criteria (example)] • The nature of the rights and interests of indirect users, et al., and their intents, affected by the judgments of AI. • The degree of reliability of the judgment of AI (compared with reliability of human judgment). • Allowable time necessary for human judgment • Ability expected to be possessed by users E) Role assignments among users With consideration of the volume of capabilities and knowledge on AI that each user is expected to have and ease of implementing necessary measures, users may be expected to play such roles as seems to be appropriate and also to bear the responsibility. F) Cooperation among stakeholders Users and data providers may be expected to cooperate with stakeholders and to work on preventive or remedial measures (including information sharing, stopping and restoration of AI, elucidation of causes, measures to prevent recurrence, etc.) in accordance with the nature, conditions, etc. of damages caused by accidents, security breaches, privacy infringement, etc. that may occur in the future or have occurred through the use of AI. What is expected reasonable from a users point of view to ensure the above effectiveness?

Published by Ministry of Internal Affairs and Communications (MIC), the Government of Japan in Draft AI Utilization Principles, Jul 17, 2018

· Transparency and explainability

The transparency and explainability of AI systems are often essential preconditions to ensure the respect, protection and promotion of human rights, fundamental freedoms and ethical principles. Transparency is necessary for relevant national and international liability regimes to work effectively. A lack of transparency could also undermine the possibility of effectively challenging decisions based on outcomes produced by AI systems and may thereby infringe the right to a fair trial and effective remedy, and limits the areas in which these systems can be legally used. While efforts need to be made to increase transparency and explainability of AI systems, including those with extra territorial impact, throughout their life cycle to support democratic governance, the level of transparency and explainability should always be appropriate to the context and impact, as there may be a need to balance between transparency and explainability and other principles such as privacy, safety and security. People should be fully informed when a decision is informed by or is made on the basis of AI algorithms, including when it affects their safety or human rights, and in those circumstances should have the opportunity to request explanatory information from the relevant AI actor or public sector institutions. In addition, individuals should be able to access the reasons for a decision affecting their rights and freedoms, and have the option of making submissions to a designated staff member of the private sector company or public sector institution able to review and correct the decision. AI actors should inform users when a product or service is provided directly or with the assistance of AI systems in a proper and timely manner. From a socio technical lens, greater transparency contributes to more peaceful, just, democratic and inclusive societies. It allows for public scrutiny that can decrease corruption and discrimination, and can also help detect and prevent negative impacts on human rights. Transparency aims at providing appropriate information to the respective addressees to enable their understanding and foster trust. Specific to the AI system, transparency can enable people to understand how each stage of an AI system is put in place, appropriate to the context and sensitivity of the AI system. It may also include insight into factors that affect a specific prediction or decision, and whether or not appropriate assurances (such as safety or fairness measures) are in place. In cases of serious threats of adverse human rights impacts, transparency may also require the sharing of code or datasets. Explainability refers to making intelligible and providing insight into the outcome of AI systems. The explainability of AI systems also refers to the understandability of the input, output and the functioning of each algorithmic building block and how it contributes to the outcome of the systems. Thus, explainability is closely related to transparency, as outcomes and ub processes leading to outcomes should aim to be understandable and traceable, appropriate to the context. AI actors should commit to ensuring that the algorithms developed are explainable. In the case of AI applications that impact the end user in a way that is not temporary, easily reversible or otherwise low risk, it should be ensured that the meaningful explanation is provided with any decision that resulted in the action taken in order for the outcome to be considered transparent. Transparency and explainability relate closely to adequate responsibility and accountability measures, as well as to the trustworthiness of AI systems.

Published by The United Nations Educational, Scientific and Cultural Organization (UNESCO) in Draft Text of The Recommendation on the Ethics of Artificial Intelligence, Nov 24, 2021

3 Ensure transparency, explainability and intelligibility

AI should be intelligible or understandable to developers, users and regulators. Two broad approaches to ensuring intelligibility are improving the transparency and explainability of AI technology. Transparency requires that sufficient information (described below) be published or documented before the design and deployment of an AI technology. Such information should facilitate meaningful public consultation and debate on how the AI technology is designed and how it should be used. Such information should continue to be published and documented regularly and in a timely manner after an AI technology is approved for use. Transparency will improve system quality and protect patient and public health safety. For instance, system evaluators require transparency in order to identify errors, and government regulators rely on transparency to conduct proper, effective oversight. It must be possible to audit an AI technology, including if something goes wrong. Transparency should include accurate information about the assumptions and limitations of the technology, operating protocols, the properties of the data (including methods of data collection, processing and labelling) and development of the algorithmic model. AI technologies should be explainable to the extent possible and according to the capacity of those to whom the explanation is directed. Data protection laws already create specific obligations of explainability for automated decision making. Those who might request or require an explanation should be well informed, and the educational information must be tailored to each population, including, for example, marginalized populations. Many AI technologies are complex, and the complexity might frustrate both the explainer and the person receiving the explanation. There is a possible trade off between full explainability of an algorithm (at the cost of accuracy) and improved accuracy (at the cost of explainability). All algorithms should be tested rigorously in the settings in which the technology will be used in order to ensure that it meets standards of safety and efficacy. The examination and validation should include the assumptions, operational protocols, data properties and output decisions of the AI technology. Tests and evaluations should be regular, transparent and of sufficient breadth to cover differences in the performance of the algorithm according to race, ethnicity, gender, age and other relevant human characteristics. There should be robust, independent oversight of such tests and evaluation to ensure that they are conducted safely and effectively. Health care institutions, health systems and public health agencies should regularly publish information about how decisions have been made for adoption of an AI technology and how the technology will be evaluated periodically, its uses, its known limitations and the role of decision making, which can facilitate external auditing and oversight.

Published by World Health Organization (WHO) in Key ethical principles for use of artificial intelligence for health, Jun 28, 2021

4 Foster responsibility and accountability

Humans require clear, transparent specification of the tasks that systems can perform and the conditions under which they can achieve the desired level of performance; this helps to ensure that health care providers can use an AI technology responsibly. Although AI technologies perform specific tasks, it is the responsibility of human stakeholders to ensure that they can perform those tasks and that they are used under appropriate conditions. Responsibility can be assured by application of “human warranty”, which implies evaluation by patients and clinicians in the development and deployment of AI technologies. In human warranty, regulatory principles are applied upstream and downstream of the algorithm by establishing points of human supervision. The critical points of supervision are identified by discussions among professionals, patients and designers. The goal is to ensure that the algorithm remains on a machine learning development path that is medically effective, can be interrogated and is ethically responsible; it involves active partnership with patients and the public, such as meaningful public consultation and debate (101). Ultimately, such work should be validated by regulatory agencies or other supervisory authorities. When something does go wrong in application of an AI technology, there should be accountability. Appropriate mechanisms should be adopted to ensure questioning by and redress for individuals and groups adversely affected by algorithmically informed decisions. This should include access to prompt, effective remedies and redress from governments and companies that deploy AI technologies for health care. Redress should include compensation, rehabilitation, restitution, sanctions where necessary and a guarantee of non repetition. The use of AI technologies in medicine requires attribution of responsibility within complex systems in which responsibility is distributed among numerous agents. When medical decisions by AI technologies harm individuals, responsibility and accountability processes should clearly identify the relative roles of manufacturers and clinical users in the harm. This is an evolving challenge and remains unsettled in the laws of most countries. Institutions have not only legal liability but also a duty to assume responsibility for decisions made by the algorithms they use, even if it is not feasible to explain in detail how the algorithms produce their results. To avoid diffusion of responsibility, in which “everybody’s problem becomes nobody’s responsibility”, a faultless responsibility model (“collective responsibility”), in which all the agents involved in the development and deployment of an AI technology are held responsible, can encourage all actors to act with integrity and minimize harm. In such a model, the actual intentions of each agent (or actor) or their ability to control an outcome are not considered.

Published by World Health Organization (WHO) in Key ethical principles for use of artificial intelligence for health, Jun 28, 2021