Prompt Injection in Automated Résumé Screening with Large Language Models: Single and Multi-Injection Settings

Source

Source name: arXiv
Source kind: paper
Authors / organization: Preet Baxi, Jiannan Xu, Jane Yi Jiang, Stefanus Jasin
Venue: arXiv: cs.AI
Published: 2026-06-25
Collected: 2026-06-26
URL: http://arxiv.org/abs/2606.27287v1
PDF: https://arxiv.org/pdf/2606.27287v1
DOI: UNKNOWN

Plain-Language Brief

The study investigates prompt injection, a strategy used by job applicants to manipulate automated resume screening systems using large language models (LLMs). The research shows that prompt injection is effective when manipulation is rare and candidate quality differences are small. However, its effectiveness diminishes as more candidates use it, and can potentially allow lower-quality candidates to outrank higher-quality ones, raising fairness concerns.

What the Document Says

The study examines prompt injection in automated resume screening using LLMs.
It shows that prompt injection improves applicant rankings when résumé quality is homogeneous and manipulation is rare.
However, its effectiveness decreases as more candidates use it, eventually collapsing when manipulation becomes widespread.
When candidate quality is heterogeneous, prompt injection can occasionally allow lower-quality candidates to outrank higher-quality ones, raising fairness concerns.
The research concludes that LLM-based screening is most vulnerable when manipulation is rare and candidate quality differences are small.

Key Concepts Mentioned

Prompt Injection
Large Language Models (LLMs)
Automated Résumé Screening

Claims Made by the Document

Prompt injection improves applicant rankings in homogeneous quality scenarios and when manipulation is rare.
Prompt injection becomes less effective as more candidates use it, eventually collapsing when manipulation becomes widespread.
In heterogeneous quality scenarios, prompt injection can occasionally allow lower-quality candidates to outrank higher-quality ones, raising fairness concerns.

Evidence Used

Controlled experiments conducted by the authors

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Large language models (LLMs) are increasingly used to screen and rank job applicants, creating incentives for candidates to strategically manipulate algorithmic hiring systems. We study prompt injection in automated résumé screening, defined as subtle self-promotional text that introduces no new qualifications but is designed to influence LLM evaluations. Using controlled experiments, we show that prompt injection reliably improves applicant rankings when résumé quality is homogeneous and few candidates inject. However, its effectiveness rapidly diminishes as more candidates inject, collapsing when manipulation becomes widespread. When candidate quality is heterogeneous, prompt injection is less effective on average, but can occasionally allow lower-quality candidates to outrank higher-quality ones, raising fairness concerns. Overall, LLM-based screening is most vulnerable when manipulation is rare and candidate quality differences are small. Code and resources are publicly available at: https://github.com/preetb1199/Prompt_Injection_ACL26