What is artificial intelligence explainability?
A working definition from MIT Sloan
artificial intelligence explainability (noun)
A quality that enables users of artificial intelligence programs to understand and trust how models operate and make decisions.
Creating successful artificial intelligence programs doesn’t end with building the right system. Stakeholders must have confidence that the programs are accurate and trustworthy.
According to research from Ida Someh, Barbara Wixom, and Cynthia Beath of the MIT Sloan Center for Information Systems Research, artificial intelligence explainability helps by ensuring users that models are “value-generating, compliant, representative, and reliable.”
There are several reasons stakeholders hesitate to trust AI. Because AI is relatively new, there isn’t an extensive list of proven use cases. Models are often opaque — AI relies on complex math and statistics, so it can be hard for average users to tell how a model works, whether it is producing accurate results, and if it is ethical and compliant.
Models can produce biased results if trained on biased data, and they also “drift” over time, meaning they can start producing inaccurate results as the world changes or incorrect data is included and replicated.
AI explainability is an emerging field, and teams working on AI projects are mostly creating the playbook as they go, the researchers write. Organizations can start by identifying units and organizations that are already creating effective AI explanations, continuing to test the most promising practices, and institutionalizing the best ones.
Working Definitions: Artificial Intelligence
MIT Sloan's Working Definitions explore the words and phrases behind emerging management ideas.
Leading the AI-Driven Organization
In person at MIT Sloan
Register Now
Scale makes firms’ automation efforts worth the investment
Whether a task is worth automating depends not only on whether machines are cheaper than human labor but also on whether the task is performed at scale to spread fixed costs.
4 areas where companies need AI guardrails
To avoid redundant investments, applications that don’t scale, and unexpected costs and risks associated with AI, organizations should determine where oversight is likely to have the greatest impact.
Increase your personal productivity in an AI-enabled workspace
To gain maximum productivity from AI, MIT Sloan’s Robert Pozen advises senior leaders to use AI as a co-worker, focus AI on the final product, and delegate work to AI without abandoning judgment.
The 5 forces creating urgency around ethical AI adoption
In his book “Boundaries of Tolerance,” MIT Sloan School of Management senior lecturer Jeffrey Saviano argues that ethical AI strategy and governance are the defining leadership challenges of our time.
Stop debating automation vs. augmentation
As organizations begin deploying agentic systems that can execute entire workflows, a consequential question is emerging: How can leaders turn agentic AI productivity gains into business growth?
How to level up systematic innovation with AI
Artificial intelligence can boost the systematic innovation of products, processes, and services. MIT Sloan professor Steven Eppinger offers four steps for making that happen.
AI and jobs: 4 takeaways from Google’s chief economist
Google’s Fabien Curto Millet examined how AI is reshaping job roles, workflows, and employee training in an address at the MIT Stone Center on Inequality and Shaping the Future of Work.
5 things to know about how companies can create value from AI
As AI tools become more widely available, competitive advantage will depend on the trust, data, expertise, operating capabilities, and work redesign companies build around them.
These new MIT Sloan courses track emerging technologies and business trends
MIT Sloan School of Management course offerings like AI-Augmented Work, Defense and Dual-Use Ventures, and Leading Agentic AI Transformation in Organizations anticipate businesses’ future needs.
‘The Collision: What AI Does to Us’
In his new book, MIT Sloan School of Management professor Eric So examines the ways AI is reshaping human cognition and offers advice on protecting your uniquely human skills while using AI.