Boge, Florian J. (2026) The Epistemic Alignment Problem of Machine Learning. In: UNSPECIFIED.

Text EpiAlign.pdf Download (144kB)

Abstract

The value alignment problem of Machine Learning is the problem of properly aligning the objectives we put into ML systems with human values. I argue that deployments of Machine Learning in research contexts create an analogous, Epistemic Alignment Problem. Given a distinction from epistemology between epistemically final and instrumental values, this problem can be seen to have two levels: In level one, an ML system is consciously misaligned with
an epistemically final value to prioritize an instrumental one. In level two, it is inadvertently misaligned with an epistemically final value. I argue that only level two should truly worry us.

---

Export/Citation:

EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL

Social Networking:

Share |

---

Item Type:	Conference or Workshop Item (UNSPECIFIED)
Creators:	Creators Email ORCID Boge, Florian J. florian-johannes.boge@tu-dortmund.de 0000-0002-1030-3393
Additional Information:	This is a preprint of a paper accepted for presentation in the 30th Biennial Meeting of the Philosophy of Science Association (PSA2026).
Keywords:	epistemic values; machine learning; alignment problem
Subjects:	Specific Sciences > Artificial Intelligence Specific Sciences > Artificial Intelligence > Machine Learning General Issues > Values In Science
Depositing User:	Prof. Dr. Florian Boge
Date Deposited:	29 May 2026 12:38
Last Modified:	29 May 2026 12:38
Item ID:	29796
Subjects:	Specific Sciences > Artificial Intelligence Specific Sciences > Artificial Intelligence > Machine Learning General Issues > Values In Science
Date:	2026
URI:	https://philsci-archive.pitt.edu/id/eprint/29796

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item