EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

How level of explanation detail affects human performance in interpretable intelligent systems: A study on explainable fact checking

Rhema Linder, Sina Mohseni, Fan Yang, Shiva K. Pentyala, Eric D. Ragan, Xia Ben Hu

Applied AI Letters · 2021-12 · 2 (4)

DOI: 10.1002/ail2.49 ↗

At a glance

Journal article in Applied AI Letters, published online on 2021-11-26. Written by Rhema Linder and 5 co-authors. Cited 30 times so far (Crossref); 78 references. The full text is freely available (open access, CC BY 4.0). Funded by: Defense Advanced Research Projects Agency.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Explainable artificial intelligence (XAI) systems aim to provide users with information to help them better understand computational models and reason about why outputs were generated. However, there are many different ways an XAI interface might present explanations, which makes designing an appropriate and effective interface an important and challenging task. Our work investigates how different types and amounts of explanatory information affect user ability to utilize explanations to understand system behavior and improve task performance. The presented research employs a system for detecting the truthfulness of news statements. In a controlled experiment, participants were tasked with using the system to assess news statements as well as to learn to predict the output of the AI. Our experiment compares various levels of explanatory information to contribute empirical data about how explanation detail can influence utility. The results show that more explanation information improves participant understanding of AI models, but the benefits come at the cost of time and attention needed to make sense of the explanation.

Funding

  • Defense Advanced Research Projects Agency

Cite

APA

Linder, R., Mohseni, S., Yang, F., Pentyala, S. K., Ragan, E. D., & Hu, X. B. (2021). How level of explanation detail affects human performance in interpretable intelligent systems: A study on explainable fact checking. Applied AI Letters, 2(4). https://doi.org/10.1002/ail2.49

Vancouver

Linder R, Mohseni S, Yang F, Pentyala SK, Ragan ED, Hu XB. How level of explanation detail affects human performance in interpretable intelligent systems: A study on explainable fact checking. Applied AI Letters. 2021;2(4). doi:10.1002/ail2.49

BibTeX
@article{Linder2021,
  author = {Linder, Rhema and Mohseni, Sina and Yang, Fan and Pentyala, Shiva K. and Ragan, Eric D. and Hu, Xia Ben},
  title = {How level of explanation detail affects human performance in interpretable intelligent systems: A study on explainable fact checking},
  journal = {Applied AI Letters},
  year = {2021},
  volume = {2},
  number = {4},
  doi = {10.1002/ail2.49}
}
Start for free →