HalluCiteChecker: A Lightweight Toolkit for Hallucinated Citation Detection and Verification in the Era of AI Scientists

TL;DR

HalluCiteChecker is a lightweight, offline toolkit designed to detect and verify hallucinated citations in scientific papers, aiming to improve review accuracy and reduce reviewer workload.

Contribution

It formalizes hallucinated citation detection as an NLP task and provides a practical, efficient toolkit that can be run offline on standard hardware.

Findings

Toolkit verifies citations in seconds on a standard laptop

Code is open-source and available on GitHub under Apache 2.0 license

Supports systematic pre-review checks to enhance publication integrity

Abstract

We introduce HalluCiteChecker, a toolkit for detecting and verifying hallucinated citations in scientific papers. While AI assistant technologies have transformed the academic writing process, including citation recommendation, they have also led to the emergence of hallucinated citations that do not correspond to any existing work. Such citations not only undermine the credibility of scientific papers but also impose an additional burden on reviewers and authors, who must manually verify their validity during the review process. In this study, we formalize hallucinated citation detection as an NLP task and provide a corresponding toolkit as a practical foundation for addressing this problem. Our package is lightweight and can perform verification in seconds on a standard laptop. It can also be executed entirely offline and runs efficiently using only CPUs. We hope that HalluCiteChecker will help reduce reviewer workload and support organizers by enabling systematic pre-review and publication checks. Our code is released under the Apache 2.0 license on GitHub and is distributed as an installable package via PyPI. A demonstration video is available on YouTube.