Cascading Hallucination in Agentic RAG: The CHARM Framework for Detection and Mitigation
Multi-step agentic retrieval-augmented generation (RAG) pipelines have demonstrated significant capability for complex reasoning tasks, yet remain vulnerable to a class of failure that existing hallucination detection mechanisms systematically miss: cascading hallucination, where errors introduced at early pipeline stages propagate and amplify across successive reasoning steps, producing confident but factually incorrect final outputs. To address this vulnerability, we formalize cascading hallucination as a distinct failure mode in agentic RAG systems, present a four-type taxonomy of cascade patterns, and introduce CHARM (Cascading Hallucination Aware Resolution and Mitigation), an architectural framework for detecting and interrupting error propagation in multi-step reasoning pipelines. CHARM comprises four components - stage-level fact verification, cross-stage consistency tracking, confidence propagation monitoring, and cascade resolution triggering - that operate alongside standard agentic RAG pipelines without requiring architectural replacement. We evaluate CHARM on HotpotQA, MuSiQue, 2WikiMultiHopQA, and a custom adversarial dataset across LangChain agentic pipeline configurations, achieving an 89.4% cascade detection rate with a 5.3% false positive rate and 215 ms +/- 18 ms average latency overhead per stage, achieving an error propagation reduction of 82.1%, compared to 18.5% for output-level detectors. Component ablations confirm that each detection module contributes meaningfully to overall cascade coverage. CHARM integrates with human-in-the-loop oversight frameworks to provide a complete reliability and governance stack for production agentic AI deployment.
Code (0)
등록된 구현이 없습니다.
Tasks
Fact VerificationResults from the Paper
Similar Papers 제목 키워드 기반
Neural Message-Passing on Attention Graphs for Hallucination Detection
Large Language Models (LLMs) often generate incorrect or unsupported content, known as hallucinations. Existing detection methods rely on heuristics or simple models over isolated computational traces such as activations…
Graph LearningHierarchical Multi-field Representations for Two-Stage E-commerce Retrieval
Dense retrieval methods typically target unstructured text data represented as flat strings. However, e-commerce catalogs often include structured information across multiple fields, such as brand, title, and description…
RetrievalSoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions
Retrieval-Augmented Generation (RAG) systems are increasingly evolving into agentic architectures where large language models autonomously coordinate multi-step reasoning, dynamic memory management, and iterative retriev…
GraphBit: A Graph-based Agentic Framework for Non-Linear Agent Orchestration
Agentic LLM frameworks that rely on prompted orchestration, where the model itself determines workflow transitions, often suffer from hallucinated routing, infinite loops, and non-reproducible execution. We introduce Gra…
Hallucinations Live in Variance
Benchmarks measure whether a model is correct. They do not measure whether a model is reliable. This distinction is largely academic for single-shot inference, but becomes critical for agentic AI systems, where a single …