Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Howell, Anthony, Wang, Jieshu, Du, Luyu, Melkers, Julia, Shah, Varshil
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2509.15122
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912592787668992
author Howell, Anthony
Wang, Jieshu
Du, Luyu
Melkers, Julia
Shah, Varshil
author_facet Howell, Anthony
Wang, Jieshu
Du, Luyu
Melkers, Julia
Shah, Varshil
contents Large language models (LLMs) are playing an increasingly integral, though largely informal, role in scholarly peer review. Yet it remains unclear whether LLMs reproduce the biases observed in human decision-making. We adapt a resume-style audit to scientific publishing, developing a multi-role LLM simulation (editor/reviewer) that evaluates a representative set of high-quality manuscripts across the physical, biological, and social sciences under randomized author identities (institutional prestige, gender, race). The audit reveals a strong and consistent institutional-prestige bias: identical papers attributed to low-prestige affiliations face a significantly higher risk of rejection, despite only modest differences in LLM-assessed quality. To probe mechanisms, we generate synthetic CVs for the same author profiles; these encode large prestige-linked disparities and an inverted prestige-tenure gradient relative to national benchmarks. The results suggest that both domain norms and prestige-linked priors embedded in training data shape paper-level outcomes once identity is visible, converting affiliation into a decisive status cue.
format Preprint
id arxiv_https___arxiv_org_abs_2509_15122
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Prestige over merit: An adapted audit of LLM bias in peer review
Howell, Anthony
Wang, Jieshu
Du, Luyu
Melkers, Julia
Shah, Varshil
Computers and Society
Large language models (LLMs) are playing an increasingly integral, though largely informal, role in scholarly peer review. Yet it remains unclear whether LLMs reproduce the biases observed in human decision-making. We adapt a resume-style audit to scientific publishing, developing a multi-role LLM simulation (editor/reviewer) that evaluates a representative set of high-quality manuscripts across the physical, biological, and social sciences under randomized author identities (institutional prestige, gender, race). The audit reveals a strong and consistent institutional-prestige bias: identical papers attributed to low-prestige affiliations face a significantly higher risk of rejection, despite only modest differences in LLM-assessed quality. To probe mechanisms, we generate synthetic CVs for the same author profiles; these encode large prestige-linked disparities and an inverted prestige-tenure gradient relative to national benchmarks. The results suggest that both domain norms and prestige-linked priors embedded in training data shape paper-level outcomes once identity is visible, converting affiliation into a decisive status cue.
title Prestige over merit: An adapted audit of LLM bias in peer review
topic Computers and Society
url https://arxiv.org/abs/2509.15122