Estimated Reading Time: 0
Technological innovations have expanded the parameters of what we thought artificial intelligence (AI) could do. And with all the recent talk surrounding ChatGPT, many experts believe AI will disrupt businesses and raise questions about what is ethical within the hiring space.
We remain at the frontier at which what we formerly considered a thought experiment is becoming tangible and part of our daily reality.
With deep learning, AI models in everyday applications have become even more complex. In fact, they are so complicated that humans often have no idea how these AI models reach their decisions.
AI models are often called ‘black box’ or ‘white box’ models. These models have a set of input systems researchers give features to, which then do a complex calculation and come to a decision.
As AI increases, there is a growing concern about the lack of transparency in its decision-making process. AI's “black box” nature can leave us uncertain and skeptical, wondering how AI arrives at its recommendations and decisions.
What is Black Box AI?
Black box AI is any AI system whose inputs and operations aren't visible to the user or another interested party. In simple terms, black box is an impenetrable system.
Deep neural networks (DNNs) and deep learning algorithms create thousands of non-linear relationships between inputs and outputs. The complexity of the relationships makes it difficult for a human to explain which features or interactions led to a specific production.
Black box AI models arrive at conclusions or decisions without explaining how they were reached. Therefore, it becomes increasingly challenging to identify why an AI model produces biased outputs and where errors in logic are occurring.
Invisibility also makes it difficult to determine who should be held accountable when outputs are flawed or dangerous. Humans have failed to understand black box AI's internal mechanisms and contributing factors.
Throughout the years, researchers have developed tools to prevent black box AI and ensure responsible AI, including:
- LIME (Local Interpretable Model-Agnostic Explanations)
- SHAP (SHAPley Additive exPlanations)
- ELI5 (Explain Like I’m 5)
- DALEX (Descriptive mAchine Learning EXplanations)
What is White Box AI?
White box AI, sometimes called glass box, is transparent about how it comes to conclusions. Humans can look at an algorithm and understand its behavior and the factors influencing its decision-making. Therefore, white box algorithms give a result and clearly readable rules.
White box AI tends to be more practical for businesses since a company can understand how these programs came to their predictions, making it easier to act on them. Companies can use them to find tangible ways to improve their workflows and know what happens if something goes wrong.
Two key elements make a model white box: features must be understandable, and the ML process must be transparent.
What is Explainable AI?
Explainable AI, created so that a typical person can understand its logic and decision-making process, is the antithesis of black-box AI.
IBM defines explainable artificial intelligence (XAI) as a set of processes and methods that allows human users to comprehend and trust the results and output created by machine learning algorithms. Explainable AI describes an AI model, its expected impact, and potential biases.
XAI helps characterize model accuracy, fairness, transparency, and outcomes in AI-powered decision-making. With XAI, humans can gain insights into the rationale behind AI recommendations and decisions, making them more trustworthy and understandable.
“Black box AI models are not necessarily bad – a black box AI designed to recommend a product to buy or a book to read is relatively safe to use. But when it comes to AI that can materially impact our lives or livelihoods, like in talent acquisition, it’s important that organizations prioritize the explainability and transparency of their AI tools for both ethical and legal reasons,” William Rose, CTO at Talent Select AI, said in a recent interview.
“If an AI model helps make a hiring decision, it’s critical that we understand and articulate why that decision or recommendation was made.”
At Talent Select AI, we're committed to providing explainable AI across all of our products. If any questions arise, we'll show you how the decisions were made.
Contact us today to see how we do it.
