Metraipolis › archive › dc_c7002c8649ab

XAI-Arena: Can LLMs Assess the Quality of XAI Explanations? — arXiv:2609.09428

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.09428
License (as archived)
CC0-1.0
Archived
2026-10-16T07:24:23.055Z
SHA-256 of the archived text
c6ca4bf1b1b3b0e649f92ebd3765651a5a26e37d3d7c91dc22ef8877c0490f40
Stable URL of this page
https://metraipolis.com/documento/dc_c7002c8649ab

How to cite

XAI-Arena: Can LLMs Assess the Quality of XAI Explanations? — arXiv:2609.09428 — arXiv (en), https://arxiv.org/abs/2609.09428 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c7002c8649ab (Metraipolis archive dc_c7002c8649ab, sha256 c6ca4bf1b1b3b0e649f92ebd3765651a5a26e37d3d7c91dc22ef8877c0490f40)
BibTeX
@misc{dcc7002c8649ab,
  title = {XAI-Arena: Can LLMs Assess the Quality of XAI Explanations? — arXiv:2609.09428},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.09428},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c7002c8649ab; sha256 c6ca4bf1b1b3b0e649f92ebd3765651a5a26e37d3d7c91dc22ef8877c0490f40},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09428. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Evaluating the quality of explanations produced by explainable AI (XAI) methods remains challenging because existing approaches often rely on subjective human judgment, limiting reproducibility, scalability, and comparability between studies. We examine whether LLMs can serve as a reproducible and scalable mechanism to make comparative assessments of the quality of XAI explanations. We introduce XAI-Arena, an LLM-as-a-judge framework for scalable, reproducible, multidimensional, and stakeholder-sensitive evaluation of XAI explanation quality. XAI-Arena then allows us to compare XAI explanations along various dimensions, namely, perceived simplicity, clarity, task adequacy, trust calibration, actionability, transparency, faithfulness, and overall interpretability. We then benchmark XAI explanation methods across various datasets, machine learning models, and stakeholder personas. Human validation shows a strong positive association between LLM-generated and human ratings (Spearman's rho=.693, p<.001). Together, LLM-based evaluations can capture systematic differences in XAI explanation quality and provide a scalable and reproducible framework for comparative assessment of XAI explanations.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-10 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.09428 — 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 2026-10-16T07:00:16.185Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).