kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
The Blame Problem in Evaluating Local Explanations and How to Tackle It
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science, Software and Computer systems, SCS.ORCID iD: 0000-0002-6846-5707
2024 (English)In: Artificial Intelligence. ECAI 2023 International Workshops - XAI^3, TACTIFUL, XI-ML, SEDAMI, RAAIT, AI4S, HYDRA, AI4AI, 2023, Proceedings, Springer Nature , 2024, p. 66-86Conference paper, Published paper (Refereed)
Abstract [en]

The number of local model-agnostic explanation techniques proposed has grown rapidly recently. One main reason is that the bar for developing new explainability techniques is low due to the lack of optimal evaluation measures. Without rigorous measures, it is hard to have concrete evidence of whether the new explanation techniques can significantly outperform their predecessors. Our study proposes a new taxonomy for evaluating local explanations: robustness, evaluation using ground truth from synthetic datasets and interpretable models, model randomization, and human-grounded evaluation. Using this proposed taxonomy, we highlight that all categories of evaluation methods, except those based on the ground truth from interpretable models, suffer from a problem we call the “blame problem.” In our study, we argue that this category of evaluation measure is a more reasonable method for evaluating local model-agnostic explanations. However, we show that even this category of evaluation measures has further limitations. The evaluation of local explanations remains an open research problem.

Place, publisher, year, edition, pages
Springer Nature , 2024. p. 66-86
Keywords [en]
Evaluation of Local Explanations, Explainability in Machine Learning, Explainable AI, Interpretability, Local Explanations, Local model-agnostic Explanations
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:kth:diva-343500DOI: 10.1007/978-3-031-50396-2_4Scopus ID: 2-s2.0-85184112932OAI: oai:DiVA.org:kth-343500DiVA, id: diva2:1837873
Conference
International Workshops of the 26th European Conference on Artificial Intelligence, ECAI 2023, Kraków, Poland, Sep 30 2023 - Oct 4 2023
Note

QC 20240219

Part of ISBN 9783031503955

Available from: 2024-02-15 Created: 2024-02-15 Last updated: 2024-02-19Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Akhavan Rahnama, Amir Hossein

Search in DiVA

By author/editor
Akhavan Rahnama, Amir Hossein
By organisation
Software and Computer systems, SCS
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 25 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf