Enoki: Efficient Multi-Level Hallucination Detection

2026-08-31

AI Summary

为解决LLM在高风险场景中的事实性问题，提出Enoki框架，通过多级幻觉检测方法，结合文本锚定关系事实的提取与验证，实现高效的事实核验和定位。

Abstract

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 them against evidence, and projects unsupported facts back to hallucinated spans. This shared representation enables claim-level verification and span-level localization without requiring separate alignment. Enoki supports LLM-based, encoder-based, and rule-based extraction regimes, balancing accuracy and inference cost through a common interface. Experiments show that Enoki remains competitive with strong claim-level systems while using fewer resources and achieves superior performance on fine-grained span- and entity-level localization. We also release EnokiQA, a dual-granularity dataset with aligned claim-level verification and span-level localization annotations.

Problem

• hallucination detection
• LLMs
• claim-level methods
• span-level methods
• factuality

Innovation

• Open Information Extraction
• Multi-Level Hallucination Detection
• Shared Representation