Metraipolis › archive › dc_a684a001cf5e

Evidence-Aligned Entity Verification for Hallucination Detection in Retrieval-Augmented Generation — arXiv:2609.08267

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.08267
License (as archived)
CC0-1.0
Archived
2026-10-16T15:05:31.716Z
SHA-256 of the archived text
0b063301d29c97051502e4c54fb534af6e66d43bcf5b0eee57cf3658451e68c7
Stable URL of this page
https://metraipolis.com/documento/dc_a684a001cf5e

How to cite

Evidence-Aligned Entity Verification for Hallucination Detection in Retrieval-Augmented Generation — arXiv:2609.08267 — arXiv (en), https://arxiv.org/abs/2609.08267 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a684a001cf5e (Metraipolis archive dc_a684a001cf5e, sha256 0b063301d29c97051502e4c54fb534af6e66d43bcf5b0eee57cf3658451e68c7)
BibTeX
@misc{dca684a001cf5e,
  title = {Evidence-Aligned Entity Verification for Hallucination Detection in Retrieval-Augmented Generation — arXiv:2609.08267},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.08267},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a684a001cf5e; sha256 0b063301d29c97051502e4c54fb534af6e66d43bcf5b0eee57cf3658451e68c7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08267. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Hallucination detection is crucial for large language models (LLMs), as hallucinated content creates significant barriers in applications requiring factual accuracy. Current detection methods mainly depend on internal signals like uncertainty and self-consistency checks, using the model's pre-trained knowledge to identify unreliable outputs. However, pre-trained knowledge may become outdated and has coverage limitations, especially for specialized or recent information. To address these limitations, retrieval-augmented generation (RAG) has emerged as a promising solution by retrieving relevant evidence at inference time, grounding outputs beyond the model's parametric knowledge. In this paper, we target a critical and practical learning problem RAG-based hallucination detection (RHD), where RAG is employed to enhance hallucination detection by addressing information updating challenges. To address RHD, we propose a novel method Evidence-Aligned Entity Verification (EAEV), which detects entity-level hallucinations by leveraging RAG to align generated entities with retrieved evidence contexts. Specifically, EAEV evaluates entity-evidence alignment through three complementary dimensions and introduces counterfactual stability analysis to ensure robust alignments under evidence perturbations. Experiments across multiple RAG benchmarks demonstrate that EAEV achieves consistent improvements over existing methods with strong generalization capabilities.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.IR).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.08267 — 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 2026-10-16T14:49:33.984Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).