SOURCE-LINKED INTELLIGENCE

Enoki: Efficient Multi-Level Hallucination Detection

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Ensuring factuality remains a critical challenge for deploying LLMs in high-stakes settings. Existing hallucination detectors usually operate at a single level: claim-level methods provide interpretable factual units, while span-level methods localize unsupported text. Bridging these views is costly, as LLM-heavy pipelines require multiple decomposition and verification calls, and modular systems need additional claim-to-span alignment. We propose Enoki, an Open Information Extraction framework for multi-level hallucination detection. Enoki extracts text-anchored relational facts, verifies the

Read original source ↗ Open in workspace

recordType

paper

region

Global