JARVIS: An Evidence-Grounded Retrieval System for Interpretable Deceptive Reviews Adjudication
For e-commerce platforms, it provides an interpretable and effective solution for detecting deceptive reviews, with substantial operational improvements.
JARVIS addresses poor generalization and lack of interpretability in deceptive review detection by using hybrid retrieval and evidence graphs, achieving precision from 0.953 to 0.988, recall from 0.830 to 0.901, 27% recall increase, 75% manual inspection reduction, and 96.4% adoption rate.
Deceptive reviews, refer to fabricated feedback designed to artificially manipulate the perceived quality of products. Within modern e-commerce ecosystems, these reviews remain a critical governance challenge. Despite advances in review-level and graph-based detection methods, two pivotal limitations remain: inadequate generalization and lack of interpretability. To address these challenges, we propose JARVIS, a framework providing Judgment via Augmented Retrieval and eVIdence graph Structures. Starting from the review to be evaluated, it retrieves semantically similar evidence via hybrid dense-sparse multimodal retrieval, expands relational signals through shared entities, and constructs a heterogeneous evidence graph. Large language model then performs evidence-grounded adjudication to produce interpretable risk assessments. Offline experiments demonstrate that JARVIS enhances performance on our constructed review dataset, achieving a precision increase from 0.953 to 0.988 and a recall boost from 0.830 to 0.901. In the production environment, our framework achieves a 27% increase in the recall volume and reduces manual inspection time by 75%. Furthermore, the adoption rate of the model-generated analysis reaches 96.4%.