% 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”.

@ARTICLE{Millire:1048885,
      author       = {Millière, Raphaël and Rathkopf, Charles},
      title        = {{A}nthropocentric bias in language model evaluation},
      journal      = {Computational linguistics},
      volume       = {.},
      issn         = {0891-2017},
      address      = {Cambridge, MA},
      publisher    = {MIT Press},
      reportid     = {FZJ-2025-04990},
      pages        = {1 - 10},
      year         = {2025},
      abstract     = {Evaluating the cognitive capacities of large language
                      models (LLMs) requires overcoming not only anthropomorphic
                      but also anthropocentric biases. This article identifies two
                      types of anthropocentric bias that have been neglected:
                      overlooking how auxiliary factors can impede LLM performance
                      despite competence (auxiliary oversight), and dismissing LLM
                      mechanistic strategies that differ from those of humans as
                      not genuinely competent (mechanistic chauvinism). Mitigating
                      these biases requires an empirical, iterative approach to
                      mapping cognitive tasks to LLM-specific capacities and
                      mechanisms, achieved by supplementing behavioral experiments
                      with mechanistic studies.},
      cin          = {INM-7},
      ddc          = {400},
      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)16},
      doi          = {10.1162/COLI.a.582},
      url          = {https://juser.fz-juelich.de/record/1048885},
}