conftrace_

poisoned document detection

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

gradient-based detection (1) document filtering (1) retrieval-augmented generation (1) adversarial attack (1) masked language model (1)

Papers

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection ACL 2025