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

VerTox is a framework that turns corpus poisoning of neural ranking models into a verifiable reward‑guided reinforcement learning problem. By fine‑tuning compact large language models with reward shaping that couples ranking distortion and factual corruption, VerTox generates fluent, low‑perplexity adversarial documents that frequently outrank target items across multiple ranking architectures, including a commercial embedding model. Experiments show near‑perfect attack success and significant degradation of downstream retrieval‑augmented generation performance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

• llms
• rag
• reinforcement-learning
• fine-tuning
• safety