VerTox: Verifiable Reward-Guided Corpus Poisoning Against Neural Ranking Models
This work proposes VerTox, the first framework to formulate corpus poisoning as a verifiable reward-guided reinforcement learning (RLVR) problem, and produces adversarial documents that frequently rank higher than target documents across major neural ranking architectures, as well as a proprietary commercial embedding...
Zhi-Qi Huang, Vivek Datla, Zhichao Xu et al.
· 0 citations