JARVIS: An Evidence-Grounded Retrieval System for Interpretable Deceptive Reviews Adjudication

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Lu, Nan, Li, Leyang, Hu, Yurong, Lin, Rui, Xu, Shaoyi
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914538677338112
author Lu, Nan
Li, Leyang
Hu, Yurong
Lin, Rui
Xu, Shaoyi
author_facet Lu, Nan
Li, Leyang
Hu, Yurong
Lin, Rui
Xu, Shaoyi
contents 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%.
format Preprint
id arxiv_https___arxiv_org_abs_2602_12941
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle JARVIS: An Evidence-Grounded Retrieval System for Interpretable Deceptive Reviews Adjudication
Lu, Nan
Li, Leyang
Hu, Yurong
Lin, Rui
Xu, Shaoyi
Information Retrieval
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%.
title JARVIS: An Evidence-Grounded Retrieval System for Interpretable Deceptive Reviews Adjudication
topic Information Retrieval
url https://arxiv.org/abs/2602.12941