Trustworthy RAG: An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Generative AI Systems

arXiv:2608.21095 · cs.SE, cs.AI, cs.CL, cs.CR, cs.IR · Submitted 2026-08-21 · Read on arXiv

cs.SE, cs.AI, cs.CL, cs.CR, cs.IR

Submitted: 2026-08-21

Updated: 2026-08-21

Code: https://github.com/GPT-Laboratory/TrustworthyRAG

Terminology

• Generative AI — 1× in this paper · explained in 2 episodes
• RAG — 1× in this paper · explained in 3 episodes

Sources

• Retrieval-Augmented Generation for Large Language Models: A Survey
• Certifiably Robust RAG against Retrieval Corruption
• Secure Retrieval-Augmented Generation against Poisoning Attacks

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties