Summary of Successfully Guiding Humans with Imperfect Instructions by Highlighting Potential Errors and Suggesting Corrections, By Lingjun Zhao et al.
Successfully Guiding Humans with Imperfect Instructions by Highlighting Potential Errors and Suggesting Corrections
by Lingjun Zhao, Khanh Nguyen, Hal Daumé III
First submitted to arxiv on: 26 Feb 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computation and Language (cs.CL); Human-Computer Interaction (cs.HC)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This research paper presents HEAR, a system that guides humans in unfamiliar situations by effectively communicating uncertainties. Unlike traditional systems that provide users with only generated instructions, HEAR warns users of potential errors and suggests corrections. This approach prevents misguidance and reduces the search space for users. The 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 presenting only instructions. Additionally, offering users possibilities to explore motivates them to make more attempts at the task, leading to a higher success rate. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary HEAR is a system that helps people make good decisions when they don’t know what to do. It gives people instructions on how to solve a problem, but also tells them if those instructions might be wrong and suggests ways to fix any mistakes. This makes it easier for people to find the right solution without getting stuck or lost. In tests with 80 people, HEAR helped people succeed more often and get to their destination faster than just giving them instructions. |
