ZeroHour
Hugging Face daily paperspublished ()ingested Elisei Rykov, Timur Ionov, Nikolay Ivanov

Enoki: Efficient Multi-Level Hallucination Detection

infoAI researchimportance 50
AI summary · glm-5.3-flash

Researchers introduce Enoki, an open information extraction framework unifying claim-level and span-level hallucination detection in LLMs at lower inference cost.

Enoki extracts text-anchored relational facts, verifies them against evidence, and projects unsupported facts back onto hallucinated spans, so claim-level verification and span-level localization share one representation without separate alignment. It supports LLM-based, encoder-based, and rule-based extraction regimes to balance accuracy against inference cost. Experiments show it stays competitive with strong claim-level systems while using fewer resources and outperforms them on fine-grained span- and entity-level localization. The authors also release EnokiQA, a dual-granularity dataset with aligned claim-level verification and span-level localization annotations.

  • Unifies claim-level verification and span-level localization through a shared representation
  • Competitive with strong claim-level detectors at lower resource cost
  • Supports LLM, encoder, and rule-based extraction regimes
  • Releases EnokiQA dual-granularity hallucination benchmark dataset
ProductsEnokiEnokiQA
Full article152 words · extracted from huggingface.co · click to collapse

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.

Text extracted automatically; images, tables and formatting may be missing. Original: https://huggingface.co/papers/2609.00581