VerTox: Verifiable Reward-Guided Corpus Poisoning Against Neural Ranking Models

Abstract

Neural ranking models have become core components of modern information retrieval systems and important building blocks of AI systems such as retrieval-augmented generation (RAG) pipelines. However, their robustness remains insufficiently understood in the presence of large language models (LLMs), which can generate fluent and deceptive content at scale. This work investigates the vulnerability of neural ranking models to corpus poisoning attacks, in which an adversary injects a small number of

Categories

Framework mappings

Suggested from the entry's categories.

@misc{huang2026vertox,
  title = {{VerTox: Verifiable Reward-Guided Corpus Poisoning Against Neural Ranking Models}},
  author = {Zhiqi Huang and Vivek Datla and Zhichao Xu and Puxuan Yu and Vivek Srikumar and Alfy Samuel},
  year = {2026},
  month = sep,
  eprint = {2609.01325},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.01325}
}