Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note2 min read

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

Source

arXiv

arxiv.org/abs/2606.27287v1

Read the source

Source

Plain-Language Brief

The study explores the impact of prompt injection, a self-promotional text strategy used by job applicants to manipulate automated hiring systems, on Large Language Models (LLMs) in résumé screening. The research shows that while prompt injection can improve an applicant's ranking when competition is low, its effectiveness decreases as more candidates use it and collapses when manipulation becomes widespread. When candidate quality varies, prompt injection can sometimes allow lower-quality candidates to outrank higher-quality ones, raising fairness concerns.

What the Document Says

  • The study focuses on prompt injection in automated résumé screening using Large Language Models (LLMs).
  • Prompt injection is defined as self-promotional text that does not add new qualifications but aims to influence LLM evaluations.
  • The experiments show that prompt injection improves applicant rankings when résumé quality is homogeneous and few candidates inject.
  • Effectiveness of prompt injection decreases rapidly as more candidates use it, collapsing when manipulation becomes widespread.
  • When candidate quality is heterogeneous, prompt injection can occasionally allow lower-quality candidates to outrank higher-quality ones.
  • The study raises fairness concerns due to the potential for lower-quality candidates to outrank higher-quality ones.
  • The research indicates 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
  • self-promotion
  • job applicants
  • candidate rankings
  • candidate quality

Claims Made by the Document

  • Prompt injection improves applicant rankings when résumé quality is homogeneous and few candidates inject.
  • Effectiveness of prompt injection decreases rapidly as more candidates use it, collapsing when manipulation becomes widespread.
  • When candidate quality is heterogeneous, prompt injection can occasionally allow lower-quality candidates to outrank higher-quality ones.
  • LLM-based screening is most vulnerable when manipulation is rare and candidate quality differences are small.

Evidence Used

  • Results from controlled experiments

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