Metraipolis › archive › dc_836e8eaf5083

Enoki: Efficient Multi-Level Hallucination Detection — arXiv:2609.00581

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.00581
License (as archived)
CC0-1.0
Archived
2026-10-17T06:41:17.512Z
SHA-256 of the archived text
d87c872d64baee66c3415f3f7bd603eff405d190510c1c854cf1ead6d1862681
Stable URL of this page
https://metraipolis.com/documento/dc_836e8eaf5083

How to cite

Enoki: Efficient Multi-Level Hallucination Detection — arXiv:2609.00581 — arXiv (en), https://arxiv.org/abs/2609.00581 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_836e8eaf5083 (Metraipolis archive dc_836e8eaf5083, sha256 d87c872d64baee66c3415f3f7bd603eff405d190510c1c854cf1ead6d1862681)
BibTeX
@misc{dc836e8eaf5083,
  title = {Enoki: Efficient Multi-Level Hallucination Detection — arXiv:2609.00581},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00581},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_836e8eaf5083; sha256 d87c872d64baee66c3415f3f7bd603eff405d190510c1c854cf1ead6d1862681},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00581. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.00581 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T06:33:38.814Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).