Large Language Models Are Biased Because They Are Large Language Models
Computational Linguistics · 01.09.2025 · 51 (3) · 885-906
DOI: 10.1162/coli_a_00558 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computational Linguistics, online erschienen am 01.09.2025. Verfasst von Philip Resnik. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 92 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
This position paper’s primary goal is to provoke thoughtful discussion about the relationship between bias and fundamental properties of large language models (LLMs). I do this by seeking to convince the reader that harmful biases are an inevitable consequence arising from the design of any large language model as LLMs are currently formulated. To the extent that this is true, it suggests that the problem of harmful bias cannot be properly addressed without a serious reconsideration of AI driven by LLMs, going back to the foundational assumptions underlying their design.
Zitieren
APA
Resnik, P. (2025). Large Language Models Are Biased Because They Are Large Language Models. Computational Linguistics, 51(3), 885-906. https://doi.org/10.1162/coli_a_00558
Vancouver
Resnik P. Large Language Models Are Biased Because They Are Large Language Models. Computational Linguistics. 2025;51(3):885-906. doi:10.1162/coli_a_00558
BibTeX
@article{Resnik2025,
author = {Resnik, Philip},
title = {Large Language Models Are Biased Because They Are Large Language Models},
journal = {Computational Linguistics},
year = {2025},
volume = {51},
number = {3},
pages = {885--906},
doi = {10.1162/coli_a_00558}
}
EUVIMED