Pub-Guard-LLM: Detecting Retracted Biomedical Articles with Reliable Explanations

TL;DR

Pub-Guard-LLM is a novel large language model-based system designed to detect retracted biomedical articles, offering multiple application modes with reliable explanations, and evaluated on a comprehensive open-source benchmark showing superior performance over baselines.

Contribution

The paper introduces Pub-Guard-LLM, the first LLM-based system for biomedical fraud detection with three deployment modes and an open benchmark, enhancing detection accuracy and explainability.

Findings

Pub-Guard-LLM outperforms baselines across all modes.

It provides more relevant and coherent explanations.

The system is open-source and applicable to real-world data.

Abstract

A significant and growing number of published scientific articles is found to involve fraudulent practices, posing a serious threat to the credibility and safety of research in fields such as medicine. We propose Pub-Guard-LLM, the first large language model-based system tailored to fraud detection of biomedical scientific articles. We provide three application modes for deploying Pub-Guard-LLM: vanilla reasoning, retrieval-augmented generation, and multi-agent debate. Each mode allows for textual explanations of predictions. To assess the performance of our system, we introduce an open-source benchmark, PubMed Retraction, comprising over 11K real-world biomedical articles, including metadata and retraction labels. We show that, across all modes, Pub-Guard-LLM consistently surpasses the performance of various baselines and provides more reliable explanations, namely explanations which are deemed more relevant and coherent than those generated by the baselines when evaluated by multiple assessment methods. By enhancing both detection performance and explainability in scientific fraud detection, Pub-Guard-LLM contributes to safeguarding research integrity with a novel, effective, open-source tool.