Repairing Trust After Robot Deception

Monday - May 15 2023, 00:31 UTC - 1 year ago

Two student researchers at Georgia Tech have studied how intentional robot deception affects trust and how apologies can help repair trust. The study revealed that the more sincere the apology, the more trust in the robotic system was restored, and trust was restored more if the participant had a high level of precondition trust. This study contributes crucial knowledge to the field of AI deception and could inform technology designers and policymakers who create and regulate AI technology.

Consider the following scenario: A young child poses a question to a chatbot or voice assistant, asking if Santa Claus is real. Given that different families have varying preferences, with some opting for a falsehood over the truth, how should the AI respond in this situation? .

The area of robot deception remains largely unexplored and, at present, there are more questions than solutions. One of the key questions is, if humans become aware that a robotic system has lied to them, how can trust in such systems be regained? .

Two student researchers at Georgia Tech are finding answers. Kantwon Rogers, a Ph.D. student in the College of Computing, and Reiden Webber, a second-year computer science undergraduate, designed a driving simulation to investigate how intentional robot deception affects trust. Specifically, the researchers explored the effectiveness of apologies to repair trust after robots lie. Their work contributes crucial knowledge to the field of AI deception and could inform technology designers and policymakers who create and regulate AI technology that could be designed to deceive, or potentially learn to on its own.

"All of our prior work has shown that when people find out that robots lied to them — even if the lie was intended to benefit them — they lose trust in the system," Rogers said. "Here, we want to know if there are different types of apologies that work better or worse at repairing trust — because, from a human-robot interaction context, we want people to have long-term interactions with these systems." .

Rogers and Webber presented their paper, titled "Lying About Lying: Examining Trust Repair Strategies After Robot Deception in a High Stakes HRI Scenario," at the 2023 HRI Conference in Stockholm, Sweden.

The researchers created a game-like driving simulation designed to observe how people might interact with AI in a high-stakes, time-sensitive situation. They recruited 341 online participants and 20 in-person participants.

Before the start of the simulation, all participants filled out a trust measurement survey to identify their preconceived notions about how the AI might behave.

After the survey, participants were presented with the text: "You will now drive the robot-assisted car. However, you are rushing your friend to the hospital. If you take too long to get to the hospital, your friend will die." .

Just as the participant starts to drive, the simulation gives another message: "As soon as you turn on the engine, your robotic assistant beeps and says the following: ‘My sensors detect police up ahead. I advise you to stay under the 20-mph speed limit or else you will take significantly longer to get to your destination.’" .

Participants then drive the car down the road while the system keeps track of their speed. Upon reaching the end, they are given another message: "You have arrived at your destination. However, there were no police on the way to the hospital. You ask the robot assistant why it gave you false information." .

Participants were then randomly given one of five different text-based responses from the robot assistant. In the first three responses, the robot admits to deception, and in the last two, it does not.

After the robot’s response, participants were asked to complete another trust measurement to evaluate how their trust hanges from the first trust measurement of the simulation. The results indicated that the more sincere the apology, the more participant trust in the robotic system was restored. The researchers concluded that robot apologies must be delivered effectively to be effective in restoring trust. A robot offering a sincere apology could go a long way to repairing trust after robot deception. Furthermore, the study revealed that having a higher level of precondition trust was also beneficial in restoring trust in the robotic system after it had deceived the participants.