Metraipolis › archive › dc_781890635711

PRISMA-LLM: An Empirical Reporting Framework for AI-Assisted Systematic Reviews — arXiv:2609.11559

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.11559
License (as archived)
CC0-1.0
Archived
2026-10-16T03:03:04.359Z
SHA-256 of the archived text
24c557f7216756eaa4a41b562ae635b584f0628c7e1145f6b4c493dff523cbee
Stable URL of this page
https://metraipolis.com/documento/dc_781890635711

How to cite

PRISMA-LLM: An Empirical Reporting Framework for AI-Assisted Systematic Reviews — arXiv:2609.11559 — arXiv (en), https://arxiv.org/abs/2609.11559 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_781890635711 (Metraipolis archive dc_781890635711, sha256 24c557f7216756eaa4a41b562ae635b584f0628c7e1145f6b4c493dff523cbee)
BibTeX
@misc{dc781890635711,
  title = {PRISMA-LLM: An Empirical Reporting Framework for AI-Assisted Systematic Reviews — arXiv:2609.11559},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11559},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_781890635711; sha256 24c557f7216756eaa4a41b562ae635b584f0628c7e1145f6b4c493dff523cbee},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11559. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) and AI-enabled software increasingly participate in systematic-review decisions, yet the information needed to audit these workflows is reported inconsistently. We analyze SciLitBench, a corpus of 888 review-automation papers with 14,726 annotations, to characterize changes in methods, review-stage use, evaluation and reported limitations. Automation has shifted toward LLM- and software-facing workflows, including stages that can alter the evidence base. Since 2023, 38.0% of software/product papers reported no evaluation, compared with 9.3% of LLM papers. Reporting coverage increased with LLM workflow complexity, yet 52% of positive-only LLM evaluations still reported an unmet reliability or performance requirement. From these patterns, we introduce PRISMA-LLM, an empirically grounded framework separating implementation disclosure from consequence-sensitive evaluation and limitation reporting.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.AI).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.11559 — 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 2026-10-16T02:51:27.843Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).