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 research investigates the impact of 'prompt injection' on automated resume screening using large language models (LLMs). Prompt injection refers to strategic manipulation in text to influence LLM evaluations. The study reveals that prompt injection can improve ranking when there are few candidates doing it, but its effectiveness decreases as more people do it. It also suggests that LLM-based screening is most vulnerable when manipulation is rare and differences in candidate quality are small.

What the Document Says

  • The research focuses on prompt injection in automated resume screening using large language models (LLMs).
  • Prompt injection involves subtle self-promotion without adding new qualifications to influence LLM evaluations.
  • In experiments, prompt injection improves applicant rankings when resume quality is homogeneous and few candidates inject.
  • As more candidates inject, the effectiveness of prompt injection diminishes, collapsing when manipulation becomes widespread.
  • When candidate quality is heterogeneous, prompt injection is less effective but can allow lower-quality candidates to outrank higher-quality ones, raising fairness concerns.
  • LLM-based screening is most vulnerable when manipulation is rare and differences in candidate quality are small.
  • The authors provide code and resources at https://github.com/preetb1199/Prompt_Injection_ACL26

Key Concepts Mentioned

  • Large Language Models (LLMs)
  • Prompt Injection
  • Automated Resume Screening
  • Job Applicants
  • Manipulation

Claims Made by the Document

  • Prompt injection improves applicant rankings in homogeneous quality scenarios.
  • The effectiveness of prompt injection diminishes as more candidates inject.
  • Prompt injection can occasionally allow lower-quality candidates to outrank higher-quality ones, raising fairness concerns.
  • LLM-based screening is most vulnerable when manipulation is rare and differences in candidate quality 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