Your new experience awaits. Try the new design now and help us make it even better

PERSPECTIVE article

Front. Artif. Intell.

Sec. Machine Learning and Artificial Intelligence

This article is part of the Research TopicSocial-Emotional Learning and Intercultural Competence in the Age of Generative AIView all articles

Computational Hermeneutics: Evaluating Generative AI as a Cultural Technology

Provisionally accepted
Cody KommersCody Kommers1*Ruth AhnertRuth Ahnert2Maria AntoniakMaria Antoniak3Emmanouil BenetosEmmanouil Benetos2Steve BenfordSteve Benford4Mercedes BunzMercedes Bunz5Baptiste CaramiauxBaptiste Caramiaux6Shauna ConcannonShauna Concannon7Martin DisleyMartin Disley8James DobsonJames Dobson9Yali DuYali Du5Edgar Duéñez-GuzmánEdgar Duéñez-Guzmán10Kerry FrancksenKerry Francksen11Evelyn GiusEvelyn Gius12Jonathan W. Y. GrayJonathan W. Y. Gray5Ryan HeuserRyan Heuser13Sarah ImmelSarah Immel8Richard Jean SoRichard Jean So14Sang LeighSang Leigh15Dalaki LivingstonDalaki Livingston16Hoyt LongHoyt Long17Meredith MartinMeredith Martin18Georgia MeyerGeorgia Meyer19Daniela MihaiDaniela Mihai20Ashley Noel-HirstAshley Noel-Hirst2Kirsten OstherrKirsten Ostherr21Deven ParkerDeven Parker22Yipeng QinYipeng Qin23Jessica RatcliffJessica Ratcliff15Emily RobinsonEmily Robinson24Karina RodriguezKarina Rodriguez25Adam SobeyAdam Sobey20Ted UnderwoodTed Underwood26Aditya VashisthaAditya Vashistha15Matthew WilkensMatthew Wilkens15Youyou WuYouyou Wu27Zheng YuanZheng Yuan5Drew HemmentDrew Hemment1
  • 1The Alan Turing Institute, London, United Kingdom
  • 2Queen Mary University of London, London, United Kingdom
  • 3University of Colorado Boulder, Boulder, United States
  • 4University of Nottingham, Nottingham, United Kingdom
  • 5King's College London, London, United Kingdom
  • 6Sorbonne Universite, Paris, France
  • 7Durham University, Durham, United Kingdom
  • 8The University of Edinburgh, Edinburgh, United Kingdom
  • 9Dartmouth College, Hanover, United States
  • 10Gibran AI, London, United Kingdom
  • 11Coventry University, Coventry, United Kingdom
  • 12Technische Universitat Darmstadt, Darmstadt, Germany
  • 13University of Cambridge, Cambridge, United Kingdom
  • 14Duke University, Durham, United States
  • 15Cornell University, Ithaca, United States
  • 16The University of Utah, Salt Lake City, United States
  • 17The University of Chicago Institute for the Study of Ancient Cultures, Chicago, United States
  • 18Princeton University, Princeton, United States
  • 19The London School of Economics and Political Science, London, United Kingdom
  • 20University of Southampton, Southampton, United Kingdom
  • 21Rice University, Houston, United States
  • 22University of Glasgow, Glasgow, United Kingdom
  • 23Cardiff University, Cardiff, United Kingdom
  • 24University of Exeter, Exeter, United Kingdom
  • 25University of Brighton, Brighton, United Kingdom
  • 26University of Illinois Urbana-Champaign, Urbana, United States
  • 27University College London, London, United Kingdom

The final, formatted version of the article will be published soon.

Select one of your emails

You have multiple emails registered with Frontiers:

Notify me on publication

Please enter your email address:

If you already have an account, please login

You don't have a Frontiers account ? You can register here

Generative AI (GenAI) systems are increasingly recognized as cultural technologies, yet current evaluation frameworks often treat culture as a variable to be measured rather than fundamental to the system's operation. Drawing on hermeneutic theory from the humanities, we argue that GenAI systems function as "context machines" that must inherently address three interpretive challenges: situatedness (meaning only emerges in context), plurality (multiple valid interpretations coexist), and ambiguity (interpretations naturally conflict). We present computational hermeneutics as an emerging framework offering an interpretive account of what GenAI systems do, and how they might do it better. We offer three principles for hermeneutic evaluation—that benchmarks should be iterative, not one-off; include people, not just machines; and measure cultural context, not just model output. This perspective offers a nascent paradigm for designing and evaluating contemporary AI systems: shifting from standardized questions about accuracy to contextual ones about meaning.

Keywords: culture, GenAI, interpretation, meaning, Societal impact

Received: 24 Nov 2025; Accepted: 06 Feb 2026.

Copyright: © 2026 Kommers, Ahnert, Antoniak, Benetos, Benford, Bunz, Caramiaux, Concannon, Disley, Dobson, Du, Duéñez-Guzmán, Francksen, Gius, Gray, Heuser, Immel, So, Leigh, Livingston, Long, Martin, Meyer, Mihai, Noel-Hirst, Ostherr, Parker, Qin, Ratcliff, Robinson, Rodriguez, Sobey, Underwood, Vashistha, Wilkens, Wu, Yuan and Hemment. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: Cody Kommers

Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.

Supplementary Material