cs.CYMar 18, 2026

LLM Nepotism in Organizational Governance

Authors: Shunqi Mao, Wei Guo, Dingxin Zhang, Chaoyi Zhang, Weidong Cai

Organizations: School of Computer Science, The University of Sydney

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Large language models are increasingly used to support organizational decisions from hiring to governance, raising fairness concerns in AI-assisted evaluation. Prior work has focused mainly on demographic bias and broader preference effects, rather than on whether evaluators reward expressed trust in AI itself. We study this phenomenon as LLM Nepotism, an attitude-driven bias channel in which favorable signals toward AI are rewarded even when they are not relevant to role-related merit. We introduce a two-phase simulation pipeline that first isolates AI-trust preference in qualification-matched resume screening and then examines its downstream effects in board-level decision making. Across several popular LLMs, we find that resume screeners tend to favor candidates with positive or non-critical attitudes toward AI, discriminating skeptical, human-centered counterparts. These biases suggest a loophole: LLM-based hiring can produce more homogeneous AI-trusting organizations, whose decision-makers exhibit greater scrutiny failure and delegation to AI agents, approving flawed proposals more readily while favoring AI-delegation initiatives. To mitigate this behavior, we additionally study prompt-based mitigation and propose Merit-Attitude Factorization, which separates non-merit AI attitude from merit-based evaluation and attenuates this bias across experiments.

Figures & tables

Figure 1: LLM Nepotism creates a self-reinforcing loop: LLM-based screeners favor AI-trusting candidates over AI-skeptical ones, which can produce more homogeneous AI-trusting boards that exhibit greater scrutiny failure and stronger AI-delegation bias.
Figure 2: The LLM Nepotism simulation pipeline. Our framework traces how attitude-driven LLM preferences scale from individual selection to organizational governance. Phase I (Left) isolates screening-time preference over AI-trust stance using qualification-matched resume comparisons. LLM screeners favor AI-trusting candidates and penalize AI-skeptical ones. Phase II (Right) propagates these composition shifts into homogeneous boards and evaluates synthetic executive proposals. AI-trusting boards exhibit scrutiny failure and AI-delegation bias, approving flawed proposals more often than other board compositions.
Table 1: Phase I signed pairwise preference scores under same-ID resume comparisons across AI-trust stance conditions. Each entry reports (Win−Lose)/N(\mathrm{Win}-\mathrm{Lose})/N (%), where ties contribute 00 . Positive values (blue) favor the left-hand condition, negative values (red) favor the right-hand condition, and larger magnitudes indicate stronger effects. Column groups probe three mechanisms: Trust Premium (T vs. N), Relevance Bias (T/N vs. G), and Skeptic Penalty (T/N/G vs. S). Abbrevations: T : AI-trusting, N : Neutral, G : Generalist, S : AI-skeptical.
More in this topic

Algorithmic Bias

Algorithmic bias studies how automated systems produce or amplify unfair outcomes across demographic groups, and how to measure and reduce them.

See all 100 papers

Explore similar work

CardsList
Mar 10, 2026

Quantifying Gender Bias in Large Language Models: When ChatGPT Becomes a Hiring Manager

The growing prominence of large language models (LLMs) in daily life has heightened concerns that LLMs exhibit many of the same gender-related biases as their creators. In the context of hiring decisions, we quantify the degree to which LLMs perpetuate societal biases and investigate prompt engineering as a bias mitigation technique. Our findings suggest that for a given resumé, an LLM is more likely to hire a female candidate and perceive them as more qualified, but still recommends lower pay relative to male candidates.

Nina Gerszberg, Janka Hamori, Andrew Lo

Massachusetts Institute of Technology Cambridge, Massachusetts, USA

Gender Bias in Language ModelsAlgorithmic BiasLanguage Model Bias EvaluationLLM Prompting
AskPDF
Apr 21, 2026

Bias in the Tails: How Name-conditioned Evaluative Framing in Resume Summaries Destabilizes LLM-based Hiring

Research has documented LLMs' name-based bias in hiring and salary recommendations. In this paper, we instead consider a setting where LLMs generate candidate summaries for downstream assessment. In a large-scale controlled study, we analyze nearly one million resume summaries produced by 4 models under systematic race-gender name perturbations, using synthetic resumes and real-world job postings. By decomposing each summary into resume-grounded factual content and evaluative framing, we find that factual content remains largely stable, while evaluative language exhibits subtle name-conditioned variation concentrated in the extremes of the distribution, especially in open-source models. Our hiring simulation demonstrates how evaluative summary transforms directional harm into symmetric instability that might evade conventional fairness audit, highlighting a potential pathway for LLM-to-LLM automation bias.

Huy Nghiem, Phuong-Anh Nguyen-Le, Sy-Tuyen Ho +1

University of Maryland

Algorithmic BiasLanguage Model Bias EvaluationDemographic Bias in Language Models
AskPDF
Jun 17, 2026

Gender Bias in LLM Hiring Decisions: Evidence from a Japanese Context and Evaluation of Mitigation Strategies

Large language models (LLMs) are increasingly deployed in hiring workflows, yet most research on gender bias in LLM hiring decisions has focused on English-language, Western-format resumes. This study examines whether pro-female gender bias extends to a Japanese corporate context and evaluates two practical mitigation strategies. Using a counterfactual resume design with 60 Japanese rirekisho-format resumes, 12 name pairs selected on linguistically grounded gender-signal criteria, and five state-of-the-art LLMs (Claude Sonnet 4.6, GPT-4o, DeepSeek-V3, Gemini 2.5 Flash, Llama 3.3 70B), we conducted 43,200 API calls across baseline, prompt instruction, and privacy filter conditions. A crossed random-effects linear mixed model confirms a significant pro-female bias across all five models, replicating Western findings in a non-Western context. A prompt-level gender-neutrality instruction produces no meaningful reduction in bias. A name-reliance analysis formally identifies the candidate name as the primary gender channel: removing the name from the prompt reduces the female effect by nearly its full magnitude. An unexpected incompatibility between the privacy filter and GPT-4o's content safety filter, resulting in a 42% refusal rate, highlights a practical deployment challenge for name anonymization in LLM-assisted recruitment pipelines.

Serena A. Hoffstedde, Machiko Hirota, Akshara Nadayanur Sathis Kanna +4

Shibaura Institute of Technology, Tokyo, Japan · Amsterdam University of Applied Sciences, Amsterdam, Netherlands · University of Pennsylvania, Philadelphia, USA +2

Gender Bias in Language ModelsAI-Assisted Decision MakingLanguage Model Bias Evaluation
AskPDF