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

arXiv: https://arxiv.org/abs/2604.19984 · HTML: https://mlsanity.com/paper/2604.19984/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 59 references that are in the map.
- First posted on arXiv 21 Apr 2026.

## Builds on (most cited first, 23 of 23)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents](https://mlsanity.com/paper/2404.10774/) (2024)
- ["Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letters](https://mlsanity.com/paper/2310.09219/) (2023)
- [Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement](https://mlsanity.com/paper/2402.11436/) (2024)
- [A Systematic Study of Bias Amplification](https://mlsanity.com/paper/2201.11706/) (2022)
- [IHEval: Evaluating Language Models on Following the Instruction Hierarchy](https://mlsanity.com/paper/2502.08745/) (2025)
- [Gender, Race, and Intersectional Bias in Resume Screening via Language Model Retrieval](https://mlsanity.com/paper/2407.20371/) (2024)
- [Thinking Fair and Slow: On the Efficacy of Structured Prompts for Debiasing Language Models](https://mlsanity.com/paper/2405.10431/) (2024)
- [The Unequal Opportunities of Large Language Models: Revealing Demographic Bias through Job Recommendations](https://mlsanity.com/paper/2308.02053/) (2023)
- [A Closer Look at System Prompt Robustness](https://mlsanity.com/paper/2502.12197/) (2025)
- [Fairness and Bias in Algorithmic Hiring: a Multidisciplinary Survey](https://mlsanity.com/paper/2309.13933/) (2023)
- [The Silicon Ceiling: Auditing GPT's Race and Gender Biases in Hiring](https://mlsanity.com/paper/2405.04412/) (2024)
- [Identifying and Improving Disability Bias in GPT-Based Resume Screening](https://mlsanity.com/paper/2402.01732/) (2024)
- [Stop! In the Name of Flaws: Disentangling Personal Names and Sociodemographic Attributes in NLP](https://mlsanity.com/paper/2405.17159/) (2024)
- [Bias Amplification in Language Model Evolution: An Iterated Learning Perspective](https://mlsanity.com/paper/2404.04286/) (2024)
- [Bias Amplification in Artificial Intelligence Systems](https://mlsanity.com/paper/1809.07842/) (2018)
- [Bias and Volatility: A Statistical Framework for Evaluating Large Language Model's Stereotypes and the Associated Generation Inconsistency](https://mlsanity.com/paper/2402.15481/) (2024)
- [Evaluating Bias in LLMs for Job-Resume Matching: Gender, Race, and Education](https://mlsanity.com/paper/2503.19182/) (2025)
- [Natural Language Processing for Human Resources: A Survey](https://mlsanity.com/paper/2410.16498/) (2024)
- [Evaluating the Promise and Pitfalls of LLMs in Hiring Decisions](https://mlsanity.com/paper/2507.02087/) (2025)
- [Cascaded Debiasing: Studying the Cumulative Effect of Multiple Fairness-Enhancing Interventions](https://mlsanity.com/paper/2202.03734/) (2022)
- [Small Changes, Large Consequences: Analyzing the Allocational Fairness of LLMs in Hiring Contexts](https://mlsanity.com/paper/2501.04316/) (2025)

## Built on by (most cited first, 1 of 1)

- [Who Gets a Token, and What Does It Carry? Unequal Name Support and Concept Access in Large Language Models](https://mlsanity.com/paper/2609.34065/) (2026)

## Abstract (arXiv)

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.