# Enoki: Efficient Multi-Level Hallucination Detection

arXiv: https://arxiv.org/abs/2609.00581 · HTML: https://mlsanity.com/paper/2609.00581/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 37 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 19 of 19)

- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference](https://mlsanity.com/paper/2412.13663/) (2024)
- [RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models](https://mlsanity.com/paper/2401.00396/) (2023)
- [Fine-grained Hallucination Detection and Editing for Language Models](https://mlsanity.com/paper/2401.06855/) (2024)
- [A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation](https://mlsanity.com/paper/2104.08704/) (2021)
- [VERISCORE: Evaluating the factuality of verifiable claims in long-form text generation](https://mlsanity.com/paper/2406.19276/) (2024)
- [Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers](https://mlsanity.com/paper/2311.09000/) (2023)
- [Neural Open Information Extraction](https://mlsanity.com/paper/1805.04270/) (2018)
- [IMoJIE: Iterative Memory-Based Joint Open Information Extraction](https://mlsanity.com/paper/2005.08178/) (2020)
- [LettuceDetect: A Hallucination Detection Framework for RAG Applications](https://mlsanity.com/paper/2502.17125/) (2025)
- [SemEval-2025 Task 3: Mu-SHROOM, the Multilingual Shared Task on Hallucinations and Related Observable Overgeneration Mistakes](https://mlsanity.com/paper/2504.11975/) (2025)
- [F-coref: Fast, Accurate and Easy to Use Coreference Resolution](https://mlsanity.com/paper/2209.04280/) (2022)
- [LSOIE: A Large-Scale Dataset for Supervised Open Information Extraction](https://mlsanity.com/paper/2101.11177/) (2021)
- [When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA](https://mlsanity.com/paper/2510.04849/) (2025)
- [HalluEntity: Benchmarking and Understanding Entity-Level Hallucination Detection](https://mlsanity.com/paper/2502.11948/) (2025)
- [Graphene: Semantically-Linked Propositions in Open Information Extraction](https://mlsanity.com/paper/1807.11276/) (2018)
- [A Survey on Open Information Extraction from Rule-based Model to Large Language Model](https://mlsanity.com/paper/2208.08690/) (2022)

## Abstract (arXiv)

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.