Modeling Disclosive Transparency in NLP Application Descriptions
Preprint
Abstract
Broader disclosive transparency$-$truth and clarity in communication regarding the function of AI systems$-$is widely considered desirable. Unfortunately, it is a nebulous concept, difficult to both define and quantify. This is problematic, as previous work has demonstrated possible trade-offs and negative consequences to disclosive transparency, such as a confusion effect, where "too much information" clouds a reader's understanding of what a system description means. Disclosive transparency's subjective nature has rendered deep study into these problems and their remedies difficult. To improve this state of affairs, We introduce neural language model-based probabilistic metrics to directly model disclosive transparency, and demonstrate that they correlate with user and expert opinions of system transparency, making them a valid objective proxy. Finally, we demonstrate the use of these metrics in a pilot study quantifying the relationships between transparency, confusion, and user perceptions in a corpus of real NLP system descriptions.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Robust Estimation of Hypernasality in Dysarthria With Acoustic Model Likelihood FeaturesIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2020
- Interpreting Interpretability: Understanding Data Scientists' Use of Interpretability Tools for Machine Learning2020
- Factors Influencing Perceived Fairness in Algorithmic Decision-Making2020
- An empirical study on the perceived fairness of realistic, imperfect machine learning models2020
- Robots and Transparency: The Multiple Dimensions of Transparency in the Context of Robot TechnologiesIEEE Robotics & Automation Magazine, 2019
- Fairness and Accountability Design Needs for Algorithmic Support in High-Stakes Public Sector Decision-Making2018
- How Much Information?2016
- A path to understanding the effects of algorithm awareness2014
- Intelligible models for classification and regression2012
- Trust in automation: Part I. Theoretical issues in the study of trust and human intervention in automated systemsErgonomics, 1994