A Special Place for Blog Lovers with a Touch of Science!

Enjoy our special posts in the fields of Earth & Planetary Sciences (EPS Blog) and Social Sciences & Arts (SSA Blog)

A Special Place for Blog Lovers with a Touch of Science!

When should someone trust an AI assistant's predictions?

Credit: MIT

Researchers help workers collaborate with artificial intelligence systems

In a busy hospital, a radiologist uses an artificial intelligence system to help her diagnose medical conditions based on patients' X-ray images. Using the AI system can help her make faster diagnoses, but how does she know when to trust the AI's predictions?

Traditionally, she doesn't. Instead, she may rely on her expertise, a confidence level provided by the system itself, or an explanation of how the algorithm made its prediction -- which may look convincing but still be wrong -- to make an estimation.

To help people better understand when to trust an AI "teammate," Massachusetts Institute of Technology researchers created a technique that guides humans to a more accurate understanding of when a machine makes correct predictions and when it makes incorrect ones. The research is supported by the U.S. National Science Foundation.

By showing people how the AI complements their abilities, the new technique could help humans make better decisions or come to conclusions faster when working with AI agents.



When should someone trust an AI assistant's predictions? Scientists are finding out.

"We propose a teaching phase where we gradually introduce humans to this AI model so they can see its weaknesses and strengths," says Hussein Mozannar of MIT. "We do this by mimicking the way people will interact with AI in practice, but we intervene to give them feedback to help them understand each interaction."

Mozannar conducted the research with Arvind Satyanarayan and David Sontag, also of MIT. The findings will be presented at the Association for the Advancement of Artificial Intelligence Conference in February.

The work focuses on the mental models humans build. If the radiologist, for example, is not sure about a case, she may ask a colleague who is an expert in a certain area. From experience and her knowledge of this colleague, she has a mental model of his or her strengths and weaknesses that she uses to assess the advice.

Humans build the same kinds of mental models when they interact with AI, so it's important that those models are accurate, Mozannar says. Cognitive science suggests that humans make decisions about complex tasks by remembering past interactions and experiences. So, the researchers designed a process that provides examples of a human and AI working together, which serve as reference points a person can draw on in the future.

"This work is an ideal example of how mathematical results can be brought to bear on solving real-world problems in AI," said Rance Cleaveland, director of NSF's Division of Computing and Communication Foundations. "The interplay between basic research and its applications is a hallmark of the kinds of impactful results NSF is looking for."

Originally published on NSF

×
Stay Informed

When you subscribe to the blog, we will send you an e-mail when there are new updates on the site so you wouldn't miss them.

Taoism
8 Inspirational Thoughts by some of the Greatest S...

Related Posts

EPS Recent Posts

06 February 2023
Earth & Planetary Sciences (EPS)
Credit: Getty images Significant advance for technologies such as quantum optics and laser displays for augmented and virtual reality As technologies keep advancing at exponential rates and demand for new devices rises accordingly, miniaturizing syst...
54 Hits
03 February 2023
Earth & Planetary Sciences (EPS)
Credit: Getty images Where do we come from? The James Webb Space Telescope (JWST) launched on Christmas Day 2021, is already transforming our understanding of planets in our Solar System and far beyond. A versatile satellite observatory, JWST has a c...
34 Hits
30 January 2023
Earth & Planetary Sciences (EPS)
Credit: Nanostructures built using software that lets researchers design objects out of DNA. Models (top) with electron microscope images of the objects (bottom); Raghu Pradeep Narayanan and Abhay Prasad, Yan lab, Arizona State University Software le...
53 Hits