MétaCan
Menu
Back to cohort
Record W3130627855 · doi:10.1177/1071181320641073

Abstraction Hierarchy Based Explainable Artificial Intelligence

2020· article· en· W3130627855 on OpenAlexaff
Murat Dikmen, Catherine M. Burns

Bibliographic record

VenueProceedings of the Human Factors and Ergonomics Society Annual Meeting · 2020
Typearticle
Languageen
FieldComputer Science
TopicExplainable Artificial Intelligence (XAI)
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsLoanHierarchyAbstractionContext (archaeology)Computer scienceQuality (philosophy)Set (abstract data type)Domain (mathematical analysis)Process (computing)Artificial intelligenceCognitionTest (biology)PerceptionPsychologyKnowledge managementFinanceBusinessEpistemologyPolitical science

Abstract

fetched live from OpenAlex

This work explores the application of Cognitive Work Analysis (CWA) in the context of Explainable Artificial Intelligence (XAI). We built an AI system using a loan evaluation data set and applied an XAI technique to obtain data-driven explanations for predictions. Using an Abstraction Hierarchy (AH), we generated domain knowledge-based explanations to accompany data-driven explanations. An online experiment was conducted to test the usefulness of AH-based explanations. Participants read financial profiles of loan applicants, the AI system’s loan approval/rejection decisions, and explanations that justify the decisions. Presence or absence of AH-based explanations was manipulated, and participants’ perceptions of the explanation quality was measured. The results showed that providing AH-based explanations helped participants learn about the loan evaluation process and improved the perceived quality of explanations. We conclude that a CWA approach can increase understandability when explaining the decisions made by AI systems.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.541
Threshold uncertainty score0.771

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0010.000
Scholarly communication0.0000.001
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.044
GPT teacher head0.253
Teacher spread0.209 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations1
Published2020
Admission routes1
Has abstractyes

Explore more

Same venueProceedings of the Human Factors and Ergonomics Society Annual MeetingSame topicExplainable Artificial Intelligence (XAI)French-language works237,207