Prompting meaning: a hermeneutic approach to optimising prompt engineering with ChatGPT

AI and Society:1-16 (forthcoming)
  Copy   BIBTEX

Abstract

Recent advances in natural language generation (NLG), such as public accessibility to ChatGPT, have sparked polarised debates about the societal impact of this technology. Popular discourse tends towards either overoptimistic hype that touts the radically transformative potentials of these systems or pessimistic critique of their technical limitations and general ‘stupidity’. Surprisingly, these debates have largely overlooked the exegetical capacities of these systems, which for many users seem to be producing meaningful texts. In this paper, we take an interdisciplinary approach that combines hermeneutics—the study of meaning and interpretation—with prompt engineering—task descriptions embedded in input to NLG systems—to study the extent to which a specific NLG system, ChatGPT, produces texts of hermeneutic value. We design prompts with the goal of optimising hermeneuticity rather than mere factual accuracy, and apply them in four different use cases combining humans and ChatGPT as readers and writers. In most cases, ChatGPT produces readable texts that respond clearly to our requests. However, increasing the specificity of prompts’ task descriptions leads to texts with intensified neutrality, indicating that ChatGPT’s optimisation for factual accuracy may actually be detrimental to the hermeneuticity of its output.

Other Versions

No versions found

Links

PhilArchive

    This entry is not archived by us. If you are the author and have permission from the publisher, we recommend that you archive it. Many publishers automatically grant permission to authors to archive pre-prints. By uploading a copy of your work, you will enable us to better index it, making it easier to find.

    Upload a copy of this work     Papers currently archived: 101,956

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

Analytics

Added to PP
2023-09-08

Downloads
55 (#401,272)

6 months
12 (#296,609)

Historical graph of downloads
How can I increase my downloads?

References found in this work

On Bullshit.Harry G. Frankfurt - 1986 - Princeton, NJ: Princeton University Press.
Narrative Identity.Paul Ricoeur - 1991 - Philosophy Today 35 (1):73-81.
AI and Phronesis.Dan Feldman & Nir Eisikovits - 2022 - Moral Philosophy and Politics 9 (2):181-199.
The Hermeneutic Circle versus Dialogue.Georgia Warnke - 2011 - Review of Metaphysics 65 (1):91-112.

Add more references