{"ID":2869445,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.15122","arxiv_id":"2509.15122","title":"Prestige over merit: An adapted audit of LLM bias in peer review","abstract":"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.","short_abstract":"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/re...","url_abs":"https://arxiv.org/abs/2509.15122","url_pdf":"https://arxiv.org/pdf/2509.15122v1","authors":"[\"Anthony Howell\",\"Jieshu Wang\",\"Luyu Du\",\"Julia Melkers\",\"Varshil Shah\"]","published":"2025-09-18T16:28:19Z","proceeding":"cs.CY","tasks":"[\"cs.CY\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}