Anthropocentric Bias in Language Model Evaluation
Computational Linguistics · 01.03.2026 · 52 (1) · 379-388
DOI: 10.1162/coli.a.582 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computational Linguistics, online erschienen am 01.03.2026. Verfasst von Raphaël Millière und 1 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Evaluating the cognitive capacities of large language models (LLMs) requires overcoming not only anthropomorphic but also anthropocentric biases. This article identifies two types of anthropocentric bias that have been neglected: overlooking how auxiliary factors can impede LLM performance despite competence (auxiliary oversight), and dismissing LLM mechanistic strategies that differ from those of humans as not genuinely competent (mechanistic chauvinism). Mitigating these biases requires an empirical, iterative approach to mapping cognitive tasks to LLM-specific capacities and mechanisms, achieved by supplementing behavioral experiments with mechanistic studies.
Zitieren
APA
Millière, R., & Rathkopf, C. (2026). Anthropocentric Bias in Language Model Evaluation. Computational Linguistics, 52(1), 379-388. https://doi.org/10.1162/coli.a.582
Vancouver
Millière R, Rathkopf C. Anthropocentric Bias in Language Model Evaluation. Computational Linguistics. 2026;52(1):379-388. doi:10.1162/coli.a.582
BibTeX
@article{Millire2026,
author = {Millière, Raphaël and Rathkopf, Charles},
title = {Anthropocentric Bias in Language Model Evaluation},
journal = {Computational Linguistics},
year = {2026},
volume = {52},
number = {1},
pages = {379--388},
doi = {10.1162/coli.a.582}
}
EUVIMED