无需编码和服务器，用浏览器插件实现AI辅助文献筛选。
TiAb Review Plugin: A Browser-Based Tool for AI-Assisted Title and Abstract Screening
- 基于浏览器扩展，利用Google Sheets共享数据，支持多人协作。
- LLM筛选召回率达94%-100%，工作量节省超48%（WSS@95）。
- 适合无编程基础的研究人员快速开展系统综述筛选。
背景：基于服务器的筛选工具需订阅费用，开源替代品则需编程技能。目标：开发一款无需代码、无服务器的人工智能辅助标题与摘要筛选浏览器插件，并评估其功能。方法：TiAb Review Plugin 是一个开源 Chrome 浏览器扩展（https://chromewebstore.google.com/detail/tiab-review-plugin/alejlnlfflogpnabpbplmnojgoeeabij），使用 Google Sheets 作为共享数据库，无需专用服务器，支持多评审员协作。用户自备 Gemini API 密钥，本地加密存储。提供三种筛选模式：手动审查、大语言模型（LLM）批量筛选、机器学习（ML）主动学习。为评估 ML 模型，我们用 TypeScript 重实现了 ASReview 默认主动学习算法（TF-IDF + 朴素贝叶斯），并通过在六个数据集上进行10折交叉验证，验证其与原Python实现结果一致。为评估 LLM，我们在基准数据集上对比了16种参数配置，最终选定最优配置（Gemini 3.0 Flash，低思维预算，TopP=0.95），并在五个公开数据集（1,038至5,628条记录，预值率0.5%至2.0%）上以敏感性提示进行验证。结果：TypeScript 分类器在所有六个数据集上的前100名排名与原始 ASReview 完全一致。对于 LLM 筛选，召回率为94%至100%，精度为2%至15%，95%召回率下的工作量节省率（WSS@95）介于48.7%至87.3%之间。结论：我们开发了一款功能完备的浏览器扩展，将 LLM 筛选与 ML 主动学习集成于无代码、无服务器环境，可直接用于系统综述筛选实践。
原文摘要 · Abstract (English)
Background: Server-based screening tools impose subscription costs, while open-source alternatives require coding skills. Objectives: We developed a browser extension that provides no-code, serverless artificial intelligence (AI)-assisted title and abstract screening and examined its functionality. Methods: TiAb Review Plugin is an open-source Chrome browser extension (available at https://chromewebstore.google.com/detail/tiab-review-plugin/alejlnlfflogpnabpbplmnojgoeeabij). It uses Google Sheets as a shared database, requiring no dedicated server and enabling multi-reviewer collaboration. Users supply their own Gemini API key, stored locally and encrypted. The tool offers three screening modes: manual review, large language model (LLM) batch screening, and machine learning (ML) active learning. For ML evaluation, we re-implemented the default ASReview active learning algorithm (TF-IDF with Naive Bayes) in TypeScript to enable in-browser execution, and verified equivalence against the original Python implementation using 10-fold cross-validation on six datasets. For LLM evaluation, we compared 16 parameter configurations across two model families on a benchmark dataset, then validated the optimal configuration (Gemini 3.0 Flash, low thinking budget, TopP=0.95) with a sensitivity-oriented prompt on five public datasets (1,038 to 5,628 records, 0.5 to 2.0 percent prevalence). Results: The TypeScript classifier produced top-100 rankings 100 percent identical to the original ASReview across all six datasets. For LLM screening, recall was 94 to 100 percent with precision of 2 to 15 percent, and Work Saved over Sampling at 95 percent recall (WSS@95) ranged from 48.7 to 87.3 percent. Conclusions: We developed a functional browser extension that integrates LLM screening and ML active learning into a no-code, serverless environment, ready for practical use in systematic review screening.
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。