用本地大模型自动选清单并填内容，让论文投稿更透明可靠。
CheckSupport: A Local LLM-Powered Tool for Automated Manuscript Submission Checklist Selection and Completion
- 分步提示策略分解报告流程，优先精准提取而非生成文本。
- 清单推荐准确率90%，条目完成率88%，单篇处理仅需12.5秒。
- 全程本地运行不传数据，适合注重隐私与可复现的研究者。
透明且标准化的报告对可复现的科学研究至关重要，但因手动选择和填写清单耗时，执行仍不一致。我们提出CheckSupport，一个开源、可本地部署的系统，利用大语言模型自动化推荐报告清单并基于证据完成清单内容。CheckSupport采用分阶段提示策略，将报告流程分解为受限推理任务，优先保证信息提取的准确性。所有推理均在本地使用指令微调模型完成，保障数据隐私，并支持可复现、可审计的工作流。在同行评审稿件语料库上评估显示，其清单推荐整体准确率达90%，条目级完成率达88%，且可在仅含CPU的硬件上运行。平均每篇文档处理耗时12.5秒，包含清单推荐与完整填写。结果表明，当大语言模型作为结构化推理组件使用时，能显著降低报告负担，推动跨学科更透明、可复现的科学报告。
原文摘要 · Abstract (English)
Transparent and standardized reporting is essential for reproducible scientific research, yet adherence to reporting guidelines remains inconsistent because of the manual effort required to select and complete checklists. We present CheckSupport, an open-source, locally deployable system that uses large language models to automate the recommendation of reporting checklists and the evidence-grounded completion of checklists for scientific manuscripts. CheckSupport employs a staged prompting strategy that decomposes reporting workflows into constrained inference tasks, prioritizing faithful extraction over generative text synthesis. All inference is performed locally using instruction-tuned models, preserving data privacy and enabling reproducible, auditable workflows. Evaluated on a corpus of peer-reviewed manuscripts, CheckSupport achieved 90% overall accuracy for checklist recommendations and 88% overall accuracy for item-level completion while operating on CPU-only hardware. On average, the wall-clock time per manuscript was 12.5 seconds, including the checklist recommendation and full checklist completion. These results demonstrate that large language models, when applied as structured inference components, can reduce reporting burden and support more transparent and reproducible scientific reporting across disciplines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。