Metraipolis › archive › dc_53dc3de00201
KnowHal: A Knowledge-Driven Benchmark for Comprehensive Multimodal Hallucination Evaluation — arXiv:2608.03782
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.03782
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T12:16:40.041Z
- SHA-256 of the archived text
af668d334e79340d0dcd27c34da7bce5d2c414782f818e1d5a458460cfe44779- Stable URL of this page
https://metraipolis.com/documento/dc_53dc3de00201
How to cite
KnowHal: A Knowledge-Driven Benchmark for Comprehensive Multimodal Hallucination Evaluation — arXiv:2608.03782 — arXiv (en), https://arxiv.org/abs/2608.03782 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_53dc3de00201 (Metraipolis archive dc_53dc3de00201, sha256 af668d334e79340d0dcd27c34da7bce5d2c414782f818e1d5a458460cfe44779)
BibTeX
@misc{dc53dc3de00201,
title = {KnowHal: A Knowledge-Driven Benchmark for Comprehensive Multimodal Hallucination Evaluation — arXiv:2608.03782},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.03782},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_53dc3de00201; sha256 af668d334e79340d0dcd27c34da7bce5d2c414782f818e1d5a458460cfe44779},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03782. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Hallucination remains a critical challenge for developing trustworthy Multimodal Large Language Models (MLLMs). While existing benchmarks mainly focus on entity, attribute, and relation hallucinations, knowledge-related failures are often investigated separately, lacking a unified evaluation framework across different hallucination dimensions. To overcome this, we propose \textbf{KnowHal}, a benchmark that explicitly incorporates knowledge hallucination into multimodal hallucination evaluation spanning four dimensions: entity, attribute, relation, and knowledge. KnowHal constructs paired positive and negative questions over shared images and entities, enabling controlled comparisons among perceptual errors, knowledge-related errors, and false-premise acceptance. The benchmark contains 1,800 samples across 10 domains and 50 categories, constructed through a semi-automated pipeline combining LLM assistance, CLIP-based filtering, and human verification. We evaluate 14 representative MLLMs on KnowHal and conduct extensive analyses. Results show that the knowledge dimension consistently presents the greatest challenge for nearly all evaluated models, while most models exhibit substantial performance degradation on negative questions, revealing limited robustness to false premises. By unifying four hallucination dimensions with paired question design, KnowHal addresses an important gap in existing evaluation frameworks and enables a more comprehensive assessment of hallucinations in MLLMs.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.03782 — 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 2026-10-31T12:05:52.853Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).