大模型
arxiv.org ·
PRISMA-LLM：面向 AI 辅助系统综述的实证报告框架
该论文分析 SciLitBench 语料（888 篇综述自动化论文、14726 条标注），刻画方法、综述阶段使用、评估与局限报告的变化。自动化已转向 LLM 与软件工作流，并涉及可能改变证据基础的阶段。2023 年以来，38.0% 的软件/产品类论文未报告任何评估，LLM 类论文为 9.3%；报告覆盖率随 LLM 工作流复杂度上升，但 52% 的仅正向结果 LLM 评估仍报告存在未满足的可靠性或性能要求。作者据此提出 PRISMA-LLM 框架，将实现披露与后果敏感评估及局限报告分离。
AI推荐理由 arXiv 新提交论文（2026-09-10），基于 SciLitBench（888 篇综述自动化论文、14726 条标注）给出可核查的量化发现：2023 年以来 38.0% 的软件/产品类论文未报告评估，而 LLM 类论文为 9.3%；52% 的仅报告正向结果的 LLM 评估仍存在未满足的可靠性或性能要求。据此提出 PRISMA-LLM 报告框架，区分实现披露与后果敏感评估。价值在于为 AI 辅助系统综述的可审计性提供实证依据与报告规范；局限是框架本身尚未见外部验证或采用证据，且属方法学/软件工程方向，对模型与 Agent 工程实践的直接影响有限。
72
正文
Computer Science > Software Engineering
arXiv:2609.11559 (cs)
[Submitted on 10 Sep 2026]
Title:PRISMA-LLM: An Empirical Reporting Framework for AI-Assisted Systematic Reviews
Authors:Miguel Zabaleta, Baihan Lin
View a PDF of the paper titled PRISMA-LLM: An Empirical Reporting Framework for AI-Assisted Systematic Reviews, by Miguel Zabaleta and 1 other authors
View PDF
HTML (experimental)
Abstract: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.
Subjects:
Software Engineering (cs.SE)
Cite as:
arXiv:2609.11559 [cs.SE]
(or
arXiv:2609.11559v1 [cs.SE] for this version)
https://doi.org/10.48550/arXiv.2609.11559
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Miguel Zabaleta [view email]
[v1]
Thu, 10 Sep 2026 13:50:10 UTC (2,364 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled PRISMA-LLM: An Empirical Reporting Framework for AI-Assisted Systematic Reviews, by Miguel Zabaleta and 1 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.SE
new
|
recent
| 2026-09
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)