# Who Gets Cited? Gender- and Majority-Bias in LLM-Driven Reference Selection

arXiv: https://arxiv.org/abs/2508.02740 · HTML: https://mlsanity.com/paper/2508.02740/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 36 references that are in the map.
- First posted on arXiv 2 Aug 2025.

## Builds on (most cited first, 4 of 4)

- [Knowledge Navigator: LLM-guided Browsing Framework for Exploratory Search in Scientific Literature](https://mlsanity.com/paper/2408.15836/) (2024)
- [Large Language Models Reflect Human Citation Patterns with a Heightened Citation Bias](https://mlsanity.com/paper/2405.15739/) (2024)
- [Exploring the applicability of Large Language Models to citation context analysis](https://mlsanity.com/paper/2409.02443/) (2024)
- [Men Set Their Own Cites High: Gender and Self-citation across Fields and over Time](https://mlsanity.com/paper/1607.00376/) (2016)

## Built on by (most cited first, 6 of 6)

- [Structurally Human, Semantically Biased: Detecting LLM-Generated References with Embeddings and GNNs](https://mlsanity.com/paper/2601.20704/) (2026)
- [Attribution Bias in Large Language Models](https://mlsanity.com/paper/2604.05224/) (2026)
- [Preliminary Guidelines for Using and Evaluating GenAI Tools to Support Systematic Literature Reviews](https://mlsanity.com/paper/2607.24991/) (2026)
- [When AI Writes, Who Gets Cited? Evidence of Citation Monoculture Across Language Models](https://mlsanity.com/paper/2608.19230/) (2026)
- [Authority Bias in Conversational Search Engines for Academic Paper Recommendation](https://mlsanity.com/paper/2609.00248/) (2026)
- [Citing Less Critically: LLMs Reshape the Rhetoric and Reach of Scientific Citation](https://mlsanity.com/paper/2609.01432/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are rapidly being adopted as research assistants, particularly for literature review and reference recommendation, yet little is known about whether they introduce demographic bias into citation workflows. This study systematically investigates gender bias in LLM-driven reference selection using controlled experiments with pseudonymous author names. We evaluate several LLMs (GPT-4o, GPT-4o-mini, Claude Sonnet, and Claude Haiku) by varying gender composition within candidate reference pools and analyzing selection patterns across fields. Our results reveal two forms of bias: a persistent preference for male-authored references and a majority-group bias that favors whichever gender is more prevalent in the candidate pool. These biases are amplified in larger candidate pools and only modestly attenuated by prompt-based mitigation strategies. Field-level analysis indicates that bias magnitude varies across scientific domains, with social sciences showing the least bias. Our findings indicate that LLMs can reinforce or exacerbate existing gender imbalances in scholarly recognition. Effective mitigation strategies are needed to avoid perpetuating existing gender disparities in scientific citation practices before integrating LLMs into high-stakes academic workflows.