RAGScope: A Leakage-Controlled, Cost-Aware Evidence-Gating Protocol for RAG Hallucination Triage

arXiv:2609.39075 · cs.CR, cs.AI · Submitted 2026-09-30 · Read on arXiv

cs.CR, cs.AI

Submitted: 2026-09-30

Updated: 2026-09-30

Comments: 8 pages, 5 figures, 8 tables. Accepted at the 2026 IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2026)

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

Terminology

Verifier — 29× in this paper · explained in 2 episodes
Hallucination — 17× in this paper · explained in 3 episodes
Calibration — 13× in this paper · explained in 7 episodes
RAG — 13× in this paper · explained in 3 episodes
Benchmark — 9× in this paper · explained in 2 episodes
Adaptation — 6× in this paper · explained in 1 episode
Consistency — 5× in this paper · explained in 3 episodes
Accuracy — 4× in this paper · explained in 1 episode
Ablation — 2× in this paper · explained in 1 episode
Generalization — 2× in this paper · explained in 13 episodes
Hallucination Detection — 2× in this paper · explained in 2 episodes
Verification — 2× in this paper · explained in 2 episodes
Cosine Similarity — 1× in this paper · explained in 3 episodes
LLM judge — 1× in this paper · explained in 2 episodes
LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
Multi-hop Reasoning — 1× in this paper · explained in 3 episodes
Regularization — 1× in this paper · explained in 3 episodes
Retrieval-Augmented Generation (RAG) — 1× in this paper · explained in 16 episodes
Robustness — 1× in this paper · explained in 5 episodes