Human in the Loop: The Key to Achieving Explainability in AI
As artificial intelligence (AI) continues to advance, there is a growing need for explainability - the ability to understand and interpret how AI models arrive at their decisions. This is especially important in high-stakes scenarios such as healthcare, finance, and justice systems, where the consequences of incorrect or biased decisions can be dire.
There are at least four distinct groups of people who are interested in explanations for an AI system, with varying motivations -
Group 1: End User Decision Makers - These are the people who use the recommendations of an AI system to make a decision, such as physicians, loan officers, managers, judges, social workers, etc. They desire explanations that can build their trust and confidence in the system’s recommendations.
Group 2: Affected Users - These are the people impacted by the recommendations made by an AI system, such as patients, loan applicants, employees, arrested individuals, at-risk children, etc. They desire explanations that can help them understand if they were treated fairly and what factor(s) could be changed to get a different result.
Group 3: Regulatory Bodies - Government agencies, charged to protect the rights of their citizens, want to ensure that decisions are made in a safe and fair manner, and that society is not negatively impacted by the decisions.?
Group 4: AI System Builders - Technical individuals (data scientists and developers) who build or deploy an AI system want to know if their system is working as expected, how to diagnose and improve it, and possibly gain insight from its decisions.
Enter human in the loop (HITL), a method of having humans involve and interpret the output of AI models. HITL can help improve the transparency and accountability of AI systems, and ultimately build trust with end-users.
But how exactly does HITL for Explainability work in practice? Let's take a closer look.
Method 1: Teaching AI to explain it's decisions
Procedure :
Framework :
This framework provides explanations?to the decisions made by the system.
For example, take a simple email spam filtering model. We can provide a specified explanation like - If an email contains a high number of misspelled words, classify it as a spam.
When we give an email with high number of misspelled words to the model, it predicts as spam and gives the explanation as "Observed high number of misspelled words".
Method 2: Providing Interactable interface to deep learning models at inference time.
Once model is built with the certain data to solve a specific task , the specifications will change continuously for the same client or one client to another client. With this approach we can provide controllable parameters to the clients or users, so that they can configure their specifications to control model behavior, instead of rebuilding their models. Providing controllable parameters to users, so that users can control AI models decisions, based on several parameters in consideration like?domain knowledge,?experience, situation, possibilities, etc.
Procedure :
Framework :
In this framework , we are providing latent discrete variables(hooks) as a controllable parameters to users. While training the model, the hook network finds the relation between the given hooks and the latent space provided by the prediction network. With these?representations from prediction network and the hook network the classification network is trained end to end. To the classification network an explainable network is attached which gives explanations in terms of latent discrete variables.
By taking the same example of email spam filtering models, the possible hooks can be -
Hook 1: If an email is sent from an unknown sender and contains job postings.
Hook 2: If an email is sent from a known sender and contains promotional content.
Client can specify whether Hook 1 can be classified as spam or not spam based on his own judgement and it can be different for other clients. For example, an Employee can filter job postings as a spam and some student may not filter it as a spam. Similarly, promotional content can be relevant to some clients and they don't consider it as a spam. Clients can configure these specifications to model at the time of inference, so that the model will take decisions and provide explanation to the predictions accordingly.
In conclusion, human in the loop is an essential component of achieving explainability in AI. By having humans involve and interpret the output of AI models, businesses can improve the transparency, accountability, and performance of their systems. This can ultimately lead to greater trust and adoption of AI technologies, and help businesses stay ahead in an increasingly competitive marketplace.