Lune

ACL Findings2026

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

Preet Baxi, Jiannan Xu, Jane Yi Jiang, Stefanus Jasin

Abstract

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

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on3

  1. Optimization-based Prompt Injection Attack to LLM-as-a-JudgeJiawen Shi, Zenghui Yuan, Yinuo Liu, Yue Huang et al.CCS 2024 · 33 citations
  2. "You Gotta be a Doctor, Lin" : An Investigation of Name-Based Bias of Large Language Models in Employment RecommendationsHuy Nghiem, John Prindle, Jieyu Zhao, Hal Daumé IIIEMNLP 2024 · 4 citations
  3. Two Tickets are Better than One: Fair and Accurate Hiring Under Strategic LLM ManipulationsLee Cohen, Connie Hong, Jack Hsieh, Judy Hanwen ShenICML 2025

Related papers

  1. Measuring Real-World Prompt Injection Attacks in LLM-based Resume ScreeningMohan Zhang, Yuqi Jia, Zhen Tan, Steven Jiang et al.USENIX Security 2026 · 4 citations
  2. Safeguarding Crowdsourcing Surveys from ChatGPT through Prompt InjectionChaofan Wang, Samuel Kernan Freire, Mo Zhang, Jing Wei et al.CSCW 2025 · 1 citation
  3. Are LLMs Reliable Rankers? Rank Manipulation via Two-Stage Token OptimizationTiancheng Xing, Jerry Li, Yixuan Du, Xiyang HuACL 2026 · 8 citations
  4. Ranking Manipulation for Conversational Search EnginesSamuel Pfrommer, Yatong Bai, Tanmay Gautam, Somayeh SojoudiEMNLP 2024 · 4 citations
  5. A Large-scale Measurement of In-Page Prompt Injections Against LLM Web AgentsSoheil Khodayari, Xuenan Zhang, Bhupendra Acharya, Giancarlo PellegrinoCCS 2026
Dusk over the sea between two cliffs drawn in fine vertical lines