TiAb Review Plugin: A Browser-Based Tool for AI-Assisted Title and Abstract Screening
Yuki Kataoka, Masahiro Banno, Michihito Kyo, Shuri Nakao, Tomoo Sato, Shunsuke Taito, Tomohiro Takayama, Takahiro Tsuge, Yasushi Tsujimoto, Ryuhei So, and Toshi A. Furukawa

TL;DR
The paper introduces TiAb Review Plugin, a browser extension enabling no-code, serverless AI-assisted title and abstract screening for systematic reviews, integrating LLM and ML active learning.
Contribution
It presents a novel, open-source, browser-based tool that combines LLM and ML active learning for efficient, no-code systematic review screening without server infrastructure.
Findings
TypeScript classifier matches Python implementation perfectly.
Achieved 94-100% recall with 2-15% precision in LLM screening.
Work Saved over Sampling at 95% recall ranged from 48.7% to 87.3%.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
