Externalist XAI?

Developers of artificial intelligence (AI) often cannot explain the inferences their neural networks make, at least not in ways that satisfy user needs. XAI—explainable artificial intelligence—aims to develop techniques for providing such explanations. XAI researchers have adopted techniques that, t...

Descripción completa

Detalles Bibliográficos
Publicado en:Theoria: A Swedish Journal of Philosophy Vol. 91; no. 2; pp. 1 - 15
Autor principal: Søgaard, Anders
Formato: Artículo
Publicado: Wiley-Blackwell Apr2025
Materias:
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=184518571&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 184518571
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        00405825
        HL0
      jtl: Theoria: A Swedish Journal of Philosophy
      issn: 00405825
      maglogo: Y
    pubinfo:
      dt: Apr2025
      vid: 91
      iid: 2
      pid: 480
      pub: Wiley-Blackwell
    artinfo:
      ui:
        184518571
        10.1111/theo.12581
      ppf: 1
      ppct: 14
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
              size: 231KB
      tig:
        atl: Externalist XAI?
      aug:
        au: Søgaard, Anders
        affil:
          Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
          Department of Communication Studies, University of Copenhagen, Copenhagen, Denmark
      su:
        Artificial intelligence
        Philosophers
        Epistemics
        Externalism (Philosophy of mind)
        Philosophical analysis
      sug:
        subj:
          Artificial intelligence
          Philosophers
          Epistemics
          Externalism (Philosophy of mind)
          Philosophical analysis
      keyword:
        explainable artificial intelligence
        externalism
        functionalism
      ab: Developers of artificial intelligence (AI) often cannot explain the inferences their neural networks make, at least not in ways that satisfy user needs. XAI—explainable artificial intelligence—aims to develop techniques for providing such explanations. XAI researchers have adopted techniques that, to philosophers, seem representationalist–internalist, leading some philosophers to call for more externalist alternatives. But is explaining AI models through causally related external factors feasible? I suggest we compare the idea of externalist XAI to so‐called functionalist XAI. Two common arguments against functionalist XAI are the Epistemic Argument and the Trust Argument, respectively. I discuss whether these arguments can be met by externalists, as well as a new, previously unnoticed challenge from random initialization.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      custom: Copyright of Theoria: A Swedish Journal of Philosophy is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use.
      item: Theoria: A Swedish Journal of Philosophy
      holder: Wiley-Blackwell
      dt:
        @attributes:
          year: 2025
    holdings:
      @attributes:
        islocal: N