Successfully Guiding Humans with Imperfect Instructions by Highlighting Potential Errors and Suggesting Corrections
It addresses the challenge of imperfect AI guidance for humans in sequential decision-making tasks, showing practical benefits of uncertainty communication.
The paper tackles the problem of language models making errors in unfamiliar situations by developing HEAR, a system that warns users of potential errors and suggests corrections in instructions, achieving a 13% increase in success rate and a 29% reduction in location error in simulated residential environments.
Language models will inevitably err in situations with which they are unfamiliar. However, by effectively communicating uncertainties, they can still guide humans toward making sound decisions in those contexts. We demonstrate this idea by developing HEAR, a system that can successfully guide humans in simulated residential environments despite generating potentially inaccurate instructions. Diverging from systems that provide users with only the instructions they generate, HEAR warns users of potential errors in its instructions and suggests corrections. This rich uncertainty information effectively prevents misguidance and reduces the search space for users. Evaluation with 80 users shows that HEAR achieves a 13% increase in success rate and a 29% reduction in final location error distance compared to only presenting instructions to users. Interestingly, we find that offering users possibilities to explore, HEAR motivates them to make more attempts at the task, ultimately leading to a higher success rate. To our best knowledge, this work is the first to show the practical benefits of uncertainty communication in a long-horizon sequential decision-making problem.