Logo PTI Logo FedCSIS

Proceedings of the 20th Conference on Computer Science and Intelligence Systems (FedCSIS)

Annals of Computer Science and Information Systems, Volume 43

Do LLMs dream of antique hermeneutics? Critical remarks on automated text interpretation

,

DOI: http://dx.doi.org/10.15439/2025F2839

Citation: Proceedings of the 20th Conference on Computer Science and Intelligence Systems (FedCSIS), M. Bolanowski, M. Ganzha, L. Maciaszek, M. Paprzycki, D. Ślęzak (eds). ACSIS, Vol. 43, pages 687–692 ()

Full text

Abstract. This study investigates the potential of large language models (LLMs) to apply hermeneutical methods rooted in philosophy, theology, sociology and literary studies in a meaningful manner. Utilising a comparative experimental design, four LLMs were prompted to interpret a variety of texts, encompassing religious, philosophical, poetic, and conversational material. The findings indicate considerable variability, an absence of reproducibility, and a substantial reliance on prompt design, model type, and language. This suggests that LLMs do not employ coherent hermeneutical strategies. Despite the automation of formal features, limitations in context sensitivity, interpretive intentionality, and epistemic grounding render LLMs ill-suited to authentic hermeneutics. The study concludes that current LLMs are incapable of replicating the depth of human interpretive practice, and calls for further interdisciplinary research to define evaluation standards for machine-assisted exegesis.

References

  1. Danner, Helmut, Hermeneutik: Zugänge, Perspektiven, Positionen, 1. Aufl ed. Freiburg: wbg Academic, 2021.
  2. G. Maier, Biblische Hermeneutik. SCM, 2014.
  3. M. Oeming, Biblische Hermeneutik. WBG, 2013.
  4. R. Maciag, “The hermeneutics of artificial text,” in Computer Sciences & Mathematics Forum, vol. 8, no. 1. MDPI, 2024, p. 94.
  5. L. Henrickson and A. Meroño-Peñuela, “Prompting meaning: a hermeneutic approach to optimising prompt engineering with chatgpt,” AI & SOCIETY, pp. 1–16, 2023.
  6. L. Tiantian and M. Carl, “Toward practical hermeneutics of fourth paradigm ai for science,” «Technology and language», vol. 5, no. 1, pp. 89–105, 2024.
  7. K. Petković, “The truth and ai: Towards a new hermeneutic of the academic subject?” Sociologija, vol. 66, no. 4, pp. 581–611, 2024.
  8. P. Pinell, “Does artificial intelligence speak our language?: A gadamerian assessment of generative language models,” Political Research Quarterly, vol. 77, no. 3, pp. 713–728, 2024.
  9. M. Heimann and A.-F. Hübener, “Circling the void: Using heidegger and lacan to think about large language models,” Cognitive Systems Research, p. 101349, 2025.
  10. A. Diržytė, “Large language models and the enhancement of human cognition: Some theoretical insights,” Filosofija. Sociologija, vol. 36, no. 1, 2025.
  11. M. Barnard and W. Otte, “Is the machine surpassing humans? large language models, structuralism, and liturgical ritual: A position paper,” International Journal of Practical Theology, vol. 28, no. 2, pp. 289–306, 2024.
  12. M. Chrostowski and A. J. Najda, “Chatgpt as a modern tool for bible teaching in confessional religious education: a german view,” Journal of Religious Education, pp. 1–20, 2024.
  13. R. Demichelis, “The hermeneutic turn of ai: Is the machine capable of interpreting?” arXiv preprint https://arxiv.org/abs/2411.12517, 2024.
  14. M. Gonzalez, “Beyond replacement: A hermeneutic phenomenological approach to human-ai collaboration,” in 2024 IEEE International Symposium on Technology and Society (ISTAS). IEEE, 2024, pp. 1–4.
  15. A. Elrod, “Uncovering theological and ethical biases in llms: An integrated hermeneutical approach employing texts from the hebrew bible,” HIPHIL Novum, vol. 9, no. 1, pp. 2–45, 2024.
  16. M. Trepczyński, “Religion, theology, and philosophical skills of llm–powered chatbots,” Disputatio Philosophica: International Journal on Philosophy and Religion, vol. 25, no. 1, pp. 19–36, 2023.
  17. K. Karches, “Hermeneutics as impediment to ai in medicine,” Theoretical Medicine and Bioethics, pp. 1–19, 2025.
  18. E. Krapp, R. Neuhaus, M. Hassenzahl, and M. Laschke, “In a quasi-social relationship with chatgpt. an autoethnography on engaging with prompt-engineered llm personas,” in Proceedings of the 13th Nordic Conference on Human-Computer Interaction, 2024, pp. 1–16.
  19. Körtner, Ulrich H. J., Der inspirierte Leser: zentrale Aspekte biblischer Hermeneutik. Göttingen [München]: Vandenhoeck und Ruprecht [Bayerische Staatsbibliothek], 1994.
  20. M. Oeming, Biblische Hermeneutik: Eine Einführung. Darmstadt: WBG, 2007.
  21. J. Resseguie, Narrative Criticism of the New Testament: An Introduction. Grand Rapids: Baker Publishing Group, 2005.
  22. N. R. Petersen, Literary Criticism for New Testament Critics. Minneapolis: Fortress Press, 1978.
  23. Wyss, Dieter, Zwischen Logos und Antilogos: Untersuchungen zur Vermittlung von Hermeneutik und Naturwissenschaft. Göttingen [München]: Vandenhoeck & Ruprecht, 1980.
  24. Schröer, Norbert and Bidlo, Oliver, “Die Entdeckung des Neuen: Qualitative Sozialforschung als Hermeneutische Wissenssoziologie.” Wiesbaden: VS Verlag für Sozialwissenschaften / Springer Fachmedien Wiesbaden GmbH, Wiesbaden, 2011, conference.
  25. U. Oevermann, “Zur analyse der struktur von soialen deutungsmustern,” 1973. [Online]. Available: https://publikationen.ub.uni-frankfurt.de/opus4/frontdoor/deliver/index/docId/4951/file/Struktur-von-Deutungsmuster-1973.pdf
  26. J. Reichertz, “Die objektive hermeneutik – darstellung und kritik,” in Qualitative Forschung, E. König and P. Zedler, Eds. Beltz Verlag, 2002, pp. 123–156.
  27. H. Niebuhr and D. Ottati, The Meaning of Revelation. Westminster: John Knox Press, 2006.
  28. D. Ritschl and H. O. Jones, Story als Rohmaterial der Theologie. München: Kaiser, 1976.
  29. B. Wacker, Narrative Theologie? München: Kösel, 1977.
  30. G. Genette, Figures III. Paris: Éditions du Seuil, 2014.
  31. A. Cornils, Vom Geist Gottes erzählen: Analysen zur Apostelgeschichte. Tübingen: Francke, 2006.
  32. J. Bailey and L. Vander Broek, Literary Forms in the New Testament: A Handbook. Westminster: John Knox, 1992.
  33. N. Perrin, “Historical criticism, literary criticism and hermeneutics: The interpretation of the parables of jesus and the gospel of mark today,” in Hermeneutical Inquiry, D. E. Klemm, Ed. Atlanta, Georgie: Scholars Press, 1986, pp. 253–266.
  34. J. A. Darr, “‘Watch How you Listen’ (Lk. 8.18): Jesus and the Rhetoric of Perception in Luke–Acts,” in The New Literary Criticism and the New Testament, ser. JSNTS, E. S. Malbon and E. V. McKnight, Eds. Sheffield: Academic Press, 1994, vol. 109, pp. 87–107.
  35. B. Dörpinghaus, “Die narratologische exegese alttestamentlicher erzähltexte: Neue perspektiven auf die jakobserzählung,” European journal of theology, vol. 31, no. 2, pp. 186–214, 2022.
  36. B. Dörpinghaus and H.-G. Wünch, “Relationships and forms in the social network of the jacob narrative: A narratological operspective,” Old Testament Essays, vol. 36, no. 2, pp. 347–367, 2023.
  37. B. Dörpinghaus, “Esau und jakob: Familien und figuren im wandel?” European Journal of Theology, vol. 32, no. 2, pp. 180–201, 2023.
  38. B. Kern, Theologie der Befreiung. UTB, 2013.
  39. G. W. Locher, Zwingli und die schweizer Reformation, ser. Die Kirche in ihrer Geschichte. Vandenhoeck & Ruprecht, 1982.
  40. V. Leppin, “Zwingli, Ulrich,” in Theologische Realenzyklopädie, H. Balz, G. Krause, and G. Müller, Eds. Berlin: de Gruyter, 2004, no. Bd. 36.
  41. W. van’t Spijker, Calvin, ser. Die Kirche in ihrer Geschichte. Vandenhoeck & Ruprecht, 2001.
  42. W. Nijenhuis, “Calvin, Johannes,” in Theologische Realenzyklopädie, H. Balz, G. Krause, and G. Müller, Eds. Berlin: de Gruyter, 1981, no. Bd. 07.
  43. E. Soja, Thirdspace: Journeys to Los Angeles and Other Real-and-Imagined Places. Wiley, 1996.
  44. H. Lefebvre and D. Nicholson-Smith, The production of space. Oxford: Blackwell, 1991, vol. 142.
  45. U. Oevermann, “Zur sache. die bedeutung von adornos methodologischem selbstverständnis für die begründung einer materialen soziologischen strukturanalyse.” in Adorno-Konferenz, L. von Friedeburg and J. Habermas, Eds., 1983, pp. 234–289.
  46. R. Fechner and J. Dörpinghaus, “No train, no pain? assessing the ability of llms for text classification with no finetuning,” in Proceedings of the Position Papers of the 19th Conference on Computer Science and Intelligence Systems (FedCSIS), Belgrade, Serbia, 2024, pp. 8–11.
  47. K. Bhattarai, I. Y. Oh, J. M. Sierra, J. Tang, P. R. Payne, Z. Abrams, and A. M. Lai, “Leveraging gpt-4 for identifying cancer phenotypes in electronic health records: a performance comparison between gpt-4, gpt-3.5-turbo, flan-t5, llama-3-8b, and spacy’s rule-based and machine learning-based methods,” JAMIA open, vol. 7, no. 3, p. ooae060, 2024.
  48. P. Ersoy and M. Erşahin, “Benchmarking llama 3 70b for code generation: A comprehensive evaluation,” Orclever Proceedings of Research and Development, vol. 4, no. 1, pp. 52–58, 2024.
  49. M. Merkel and J. Dörpinghaus, “A case study on the transformative potential of ai in software engineering on leetcode and chatgpt,” arXiv preprint https://arxiv.org/abs/2501.03639, 2025.
  50. P. Törnberg, “How to use llms for text analysis,” arXiv preprint https://arxiv.org/abs/2307.13106, 2023.
  51. T. Fu, R. Ferrando, J. Conde, C. Arriaga, and P. Reviriego, “Why do large language models (llms) struggle to count letters?” arXiv preprint https://arxiv.org/abs/2412.18626, 2024.
  52. L. Nguyen and Y. Yan, “Evaluating the structural awareness of large language models on graphs: Can they count substructures?” Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD ’24), 2024.
  53. R. H. Tai, L. R. Bentley, X. Xia, J. M. Sitt, S. C. Fankhauser, A. M. Chicas-Mosier, and B. G. Monteith, “An examination of the use of large language models to aid analysis of textual data,” International Journal of Qualitative Methods, vol. 23, p. 16094069241231168, 2024.
  54. W. S. Saba, “Llms’ understanding of natural language revealed,” arXiv preprint https://arxiv.org/abs/2407.19630, 2024.
  55. A. Videla, “Echoes of intelligence: Textual interpretation and large language models,” Queue, vol. 21, no. 3, pp. 36–53, 2023.
  56. P. Villalobos, A. Ho, J. Sevilla, T. Besiroglu, L. Heim, and M. Hobbhahn, “Position: Will we run out of data? limits of llm scaling based on human-generated data,” in Forty-first International Conference on Machine Learning, 2024.
  57. J. Wu, S. Yang, R. Zhan, Y. Yuan, L. S. Chao, and D. F. Wong, “A survey on llm-generated text detection: Necessity, methods, and future directions,” Computational Linguistics, pp. 1–66, 2025.