RAGSentinel: Certifiable Geometric Consensus for Robust Retrieval-Augmented Generation

arXiv:2608.23965 · cs.CR, cs.AI, cs.IR, cs.LG · Submitted 2026-08-25 · Read on arXiv

cs.CR, cs.AI, cs.IR, cs.LG

Submitted: 2026-08-25

Updated: 2026-08-25

Comments: To appear in EMNLP 2026 (Main Conference)

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• RAG — 40× in this paper · explained in 3 episodes
• Consistency — 12× in this paper · explained in 3 episodes
• Robustness — 9× in this paper · explained in 5 episodes
• Accuracy — 8× in this paper · explained in 1 episode
• Aggregation — 5× in this paper · explained in 1 episode
• Embeddings — 4× in this paper · explained in 2 episodes
• Natural Questions — 4× in this paper
• Benchmark — 3× in this paper · explained in 2 episodes
• Clustering — 3× in this paper · explained in 2 episodes
• Computational overhead — 3× in this paper · explained in 2 episodes
• Cosine Similarity — 3× in this paper · explained in 3 episodes
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Grounding — 3× in this paper · explained in 3 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Adversarial Decoding — 2× in this paper
• Benchmarking — 2× in this paper · explained in 3 episodes
• Contrastive Learning — 2× in this paper · explained in 5 episodes
• Failure Modes — 2× in this paper · explained in 3 episodes
• Retrieval-Augmented Generation (RAG) — 2× in this paper · explained in 16 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Adversarial Attacks — 1× in this paper · explained in 1 episode
• Arbiter — 1× in this paper · explained in 1 episode
• Attack Success Rate (ASR) — 1× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Federated Learning — 1× in this paper · explained in 15 episodes
• Homogeneity — 1× in this paper · explained in 2 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• Knowledge Distillation — 1× in this paper · explained in 11 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• National Broadcasting Company — 1× in this paper
• Prompt Injection Attack — 1× in this paper
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• GPT-4 Technical Report
• Is My Data in Your Retrieval Database? Membership Inference Attacks Against Retrieval Augmented Generation
• MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
• Discovering Latent Knowledge in Language Models Without Supervision
• M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
• The Llama 3 Herd of Models
• Unsupervised Dense Information Retrieval with Contrastive Learning
• Mistral 7B
• Ignore Previous Prompt: Attack Techniques For Language Models
• Improving Text Embeddings with Large Language Models
• Certifiably Robust RAG against Retrieval Corruption
• Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
• Benchmarking Poisoning Attacks against Retrieval-Augmented Generation
• TrustRAG: Enhancing Robustness and Trustworthiness in Retrieval-Augmented Generation

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs