Are we still able to recognize pearls? Machine-driven peer review and the risk to creativity: An explainable RAG-XAI detection framework with markers extraction
This addresses the problem of epistemic homogenization in science for researchers and publishers, though it is incremental as it builds on existing detection and explainable AI methods.
The paper tackles the risk that machine-generated peer reviews could automate editorial decisions and penalize unconventional research, by introducing an explainable RAG-XAI framework for detecting automated review patterns. The framework achieves near-perfect detection with 99.61% accuracy, AUC-ROC above 0.999, and F1-scores of 0.9925, significantly outperforming a logistic regression baseline.
The integration of large language models (LLMs) into peer review raises a concern beyond authorship and detection: the potential cascading automation of the entire editorial process. As reviews become partially or fully machine-generated, it becomes plausible that editorial decisions may also be delegated to algorithmic systems, leading to a fully automated evaluation pipeline. They risk reshaping the criteria by which scientific work is assessed. This paper argues that machine-driven assessment may systematically favor standardized, pattern-conforming research while penalizing unconventional and paradigm-shifting ideas that require contextual human judgment. We consider that this shift could lead to epistemic homogenization, where researchers are implicitly incentivized to optimize their work for algorithmic approval rather than genuine discovery. To address this risk, we introduce an explainable framework (RAG-XAI) for assessing review quality and detecting automated patterns using markers LLM extractor, aiming to preserve transparency, accountability and creativity in science. The proposed framework achieves near-perfect detection performance, with XGBoost, Random Forest and LightGBM reaching 99.61% accuracy, AUC-ROC above 0.999 and F1-scores of 0.9925 on the test set, while maintaining extremely low false positive rates (<0.23%) and false negative rates (~0.8%). In contrast, the logistic regression baseline performs substantially worse (89.97% accuracy, F1-score 0.8314). Feature importance and SHAP analyses identify absence of personal signals and repetition patterns as the dominant predictors. Additionally, the RAG component achieves 90.5% top-1 retrieval accuracy, with strong same-class clustering in the embedding space, further supporting the reliability of the framework's outputs.