Artificial mental phenomena: Psychophysics as a framework to detect perception biases in AI models

Lizhen Liang, Daniel E. Acuna

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Detecting biases in artificial intelligence has become difficult because of the impenetrable nature of deep learning. The central difficulty is in relating unobservable phenomena deep inside models with observable, outside quantities that we can measure from inputs and outputs. For example, can we detect gendered perceptions of occupations (e.g., female librarian, male electrician) using questions to and answers from a word embedding-based system? Current techniques for detecting biases are often customized for a task, dataset, or method, affecting their generalization. In this work, we draw from Psychophysics in Experimental Psychology-meant to relate quantities from the real world (i.e., “Physics”) into subjective measures in the mind (i.e., “Psyche”)-to propose an intellectually coherent and generalizable framework to detect biases in AI. Specifically, we adapt the two-alternative forced choice task (2AFC) to estimate potential biases and the strength of those biases in black-box models. We successfully reproduce previously-known biased perceptions in word embeddings and sentiment analysis predictions. We discuss how concepts in experimental psychology can be naturally applied to understanding artificial mental phenomena, and how psychophysics can form a useful methodological foundation to study fairness in AI.

Original languageEnglish (US)
Title of host publicationFAT* 2020 - Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency
PublisherAssociation for Computing Machinery, Inc
Pages403-412
Number of pages10
ISBN (Electronic)9781450369367
DOIs
StatePublished - Jan 27 2020
Event3rd ACM Conference on Fairness, Accountability, and Transparency, FAT* 2020 - Barcelona, Spain
Duration: Jan 27 2020Jan 30 2020

Publication series

NameFAT* 2020 - Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency

Conference

Conference3rd ACM Conference on Fairness, Accountability, and Transparency, FAT* 2020
CountrySpain
CityBarcelona
Period1/27/201/30/20

Keywords

  • Artificial Psychophysics
  • Biases in Sentiment Analysis
  • Biases in word embeddings
  • Two-alternative forced choice task

ASJC Scopus subject areas

  • Business, Management and Accounting(all)
  • Engineering(all)

Fingerprint Dive into the research topics of 'Artificial mental phenomena: Psychophysics as a framework to detect perception biases in AI models'. Together they form a unique fingerprint.

  • Cite this

    Liang, L., & Acuna, D. E. (2020). Artificial mental phenomena: Psychophysics as a framework to detect perception biases in AI models. In FAT* 2020 - Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency (pp. 403-412). (FAT* 2020 - Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency). Association for Computing Machinery, Inc. https://doi.org/10.1145/3351095.3375623