Justifying black-box predictions with domain knowledge

Joeri Peters; Floris Bex; Henry Prakken

Justifying black-box predictions with domain knowledge

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

AF-CBA uses case-based argumentation to justify classifier predictions by arguing about differences between cases. We extend the mechanism by modelling which differences can compensate for each other by constructing arguments using domain knowledge. This involves a secondary argumentation framework. To assist experts in defining the appropriate domain knowledge, we use a rule-based classifier for semi-automated knowledge induction. We use the resulting rule set to derive arguments and demonstrate this with an evaluation procedure.

Original language	English
Title of host publication	Proceedings of the 20th International Conference on Artificial Intelligence and Law
Editors	Juliano Maranhao
Publisher	Association for Computing Machinery
Pages	102-111
ISBN (Electronic)	979-8-4007-1939-4
Publication status	Published - 2025

Cite this

@inproceedings{4a58acd5535546009c282c83c5ea75b8,

title = "Justifying black-box predictions with domain knowledge",

abstract = "AF-CBA uses case-based argumentation to justify classifier predictions by arguing about differences between cases. We extend the mechanism by modelling which differences can compensate for each other by constructing arguments using domain knowledge. This involves a secondary argumentation framework. To assist experts in defining the appropriate domain knowledge, we use a rule-based classifier for semi-automated knowledge induction. We use the resulting rule set to derive arguments and demonstrate this with an evaluation procedure.",

author = "Joeri Peters and Floris Bex and Henry Prakken",

year = "2025",

language = "English",

pages = "102--111",

editor = "Juliano Maranhao",

booktitle = "Proceedings of the 20th International Conference on Artificial Intelligence and Law",

publisher = "Association for Computing Machinery",

address = "United States",

}

Justifying black-box predictions with domain knowledge. / Peters, Joeri ; Bex, Floris ; Prakken, Henry.
Proceedings of the 20th International Conference on Artificial Intelligence and Law. ed. / Juliano Maranhao. Association for Computing Machinery, 2025. p. 102-111.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Justifying black-box predictions with domain knowledge

AU - Peters, Joeri

AU - Bex, Floris

AU - Prakken, Henry

PY - 2025

Y1 - 2025

N2 - AF-CBA uses case-based argumentation to justify classifier predictions by arguing about differences between cases. We extend the mechanism by modelling which differences can compensate for each other by constructing arguments using domain knowledge. This involves a secondary argumentation framework. To assist experts in defining the appropriate domain knowledge, we use a rule-based classifier for semi-automated knowledge induction. We use the resulting rule set to derive arguments and demonstrate this with an evaluation procedure.

AB - AF-CBA uses case-based argumentation to justify classifier predictions by arguing about differences between cases. We extend the mechanism by modelling which differences can compensate for each other by constructing arguments using domain knowledge. This involves a secondary argumentation framework. To assist experts in defining the appropriate domain knowledge, we use a rule-based classifier for semi-automated knowledge induction. We use the resulting rule set to derive arguments and demonstrate this with an evaluation procedure.

M3 - Conference contribution

SP - 102

EP - 111

BT - Proceedings of the 20th International Conference on Artificial Intelligence and Law

A2 - Maranhao, Juliano

PB - Association for Computing Machinery

ER -

Justifying black-box predictions with domain knowledge

Abstract

Fingerprint

Cite this