% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@INPROCEEDINGS{Rathkopf:1031976,
      author       = {Rathkopf, Charles},
      title        = {{H}allucination, justification, and the role of generative
                      {AI} in science},
      reportid     = {FZJ-2024-05900},
      year         = {2024},
      abstract     = {Generative AI models are now being used to create synthetic
                      climate data to improve the accuracy of climate models, and
                      to construct virtual molecules which can then be synthesized
                      for medical applications. But generative AI models are also
                      notorious for their disposition to “hallucinate.” A
                      recent Nature editorial defines hallucination as a process
                      in which a generative model “makes up incorrect answers”
                      (Jones, 2024). This raises an obvious puzzle. If generative
                      models are prone to fabricating incorrect answers, how can
                      they be used responsibly? In this talk I provide an analysis
                      of the phenomenon of hallucination, and give special
                      attention to diffusion models trained on scientific data
                      (rather than transformers trained on natural language.) The
                      goal of the paper is to work out how generative AI can be
                      made compatible with reliabilist epistemology. I draw a
                      distinction between parameter-space and feature-space
                      deviations from the training data, and argue that
                      hallucination is a subset of the latter. This allows us to
                      recognize a class of cases in which the threat of
                      hallucination simply does not arise. Among the remaining
                      cases, I draw an additional distinction between deviations
                      that are discoverable by algorithmic means, and those that
                      are not. I then argue that if a deviation is discoverable by
                      algorithmic means, reliability is not threatened, and that
                      if the deviation is not so discoverable, then the generative
                      model that produced it will be relevantly similar to other
                      discovery procedures, and can therefore be accommodated
                      within the reliabilist framework.},
      month         = {Oct},
      date          = {2024-10-25},
      organization  = {Uppsala Vienna AI Colloquium, (online
                       event), 25 Oct 2024},
      subtyp        = {Invited},
      cin          = {INM-7},
      cid          = {I:(DE-Juel1)INM-7-20090406},
      pnm          = {5255 - Neuroethics and Ethics of Information (POF4-525)},
      pid          = {G:(DE-HGF)POF4-5255},
      typ          = {PUB:(DE-HGF)31},
      url          = {https://juser.fz-juelich.de/record/1031976},
}