A single query-specific poisoned document, built by extracting and iteratively refining an adversarial chain-of-thought, can substantially degrade reasoning accuracy in retrieval-augmented LLM systems.
Smartrag: Jointly learn rag-related tasks from the environment feedback
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Process supervision via RAG-Gym produces more reliable and generalizable search agents, with gains driven by higher-quality queries on out-of-domain multi-hop tasks.
citing papers explorer
-
AdversarialCoT: Single-Document Retrieval Poisoning for LLM Reasoning
A single query-specific poisoned document, built by extracting and iteratively refining an adversarial chain-of-thought, can substantially degrade reasoning accuracy in retrieval-augmented LLM systems.
-
Supervising the search process produces reliable and generalizable information-seeking agents
Process supervision via RAG-Gym produces more reliable and generalizable search agents, with gains driven by higher-quality queries on out-of-domain multi-hop tasks.
- When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering