Metraipolis › archive › dc_86e366dd577e

NewsBench: Expert-Grounded Evaluation of Epistemic Quality in AI News Reporting — arXiv:2610.33240

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.33240
License (as archived): CC0-1.0
Archived: 2026-10-27T07:56:30.268Z
SHA-256 of the archived text: 3afe8249a6a854db5689f014ef12785ce2e5a33e95a8698b9c7589f99d9b73c3
Stable URL of this page: https://metraipolis.com/documento/dc_86e366dd577e

How to cite

NewsBench: Expert-Grounded Evaluation of Epistemic Quality in AI News Reporting — arXiv:2610.33240 — arXiv (en), https://arxiv.org/abs/2610.33240 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_86e366dd577e (Metraipolis archive dc_86e366dd577e, sha256 3afe8249a6a854db5689f014ef12785ce2e5a33e95a8698b9c7589f99d9b73c3)

BibTeX

@misc{dc86e366dd577e,
  title = {NewsBench: Expert-Grounded Evaluation of Epistemic Quality in AI News Reporting — arXiv:2610.33240},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.33240},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_86e366dd577e; sha256 3afe8249a6a854db5689f014ef12785ce2e5a33e95a8698b9c7589f99d9b73c3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33240. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As frontier AI systems increasingly serve as sources of political and current-events information, evaluating the epistemic quality of their responses is now especially consequential. Existing evaluations often focus narrowly on ideological alignment, rely on measures not validated for this setting, or depend on reference labels derived from public opinion or non-expert annotation, potentially producing misleading or miscalibrated results. To address these limitations, we introduce NewsBench, an expert-grounded benchmark that reframes evaluation around editorial standards developed by senior practitioners in journalism, policy, and intelligence analysis. NewsBench operationalizes quality across three dimensions, source quality, factuality, and neutrality, using a two-phase pipeline in which domain experts first define and calibrate evaluation guidelines, which are then transferred to automated AI judges validated against expert-adjudicated gold labels. The benchmark includes approximately $3,000$ evaluation prompts, with roughly $500$ refreshed monthly to capture emerging current events, roughly $2,500$ human expert-annotated items for calibration and validation, and a suite of AI judges designed to enable scalable evaluation. To validate our methodology, we report both inter-rater reliability among human experts and AI judge--human agreement across all three dimensions. Finally, we apply NewsBench to four frontier models, revealing distinct and non-overlapping failure profiles in sourcing, factuality, and neutrality.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.33240 — 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 2026-10-27T07:55:30.624Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).