# A Modular LLM Framework for Explainable Price Outlier Detection

Source: [A Modular LLM Framework for Explainable Price Outlier Detection](<https://www.sota2.com/research/paper/69c21a620636e5bf4afc4620>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-25T05:00:04.214Z

Authors: Shadi Sartipi, John Wu, Sina Ghotbi, Nikhita Vedula, Shervin Malmasi

Published: 2026-03-21T04:11:22.000Z

## Abstract

Detecting product price outliers is important for retail and e-commerce stores as erroneous or unexpectedly high prices adversely affect competitiveness, revenue, and consumer trust. Classical techniques offer simple thresholds while ignoring the rich semantic relationships among product attributes. We propose an agentic Large Language Model (LLM) framework that treats outlier price flagging as a reasoning task grounded in related product detection and comparison. The system processes the prices of target products in three stages: (i) relevance classification selects price-relevant similar products using product descriptions and attributes; (ii) relative utility assessment evaluates the target product against each similar product along price influencing dimensions (e.g., brand, size, features); (iii) reasoning-based decision aggregates these justifications into an explainable price outlier judgment. The framework attains over 75% agreement with human auditors on a test dataset, and outperforms zero-shot and retrieval based LLM techniques. Ablation studies show the sensitivity of the method to key hyper-parameters and testify on its flexibility to be applied to cases with different accuracy requirement and auditor agreements.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Price Outlier Detection on Silver Set (SS)](<https://www.sota2.com/research/sota/price-outlier-detection-on-silver-set-ss.md>): Price Outlier Detection; Silver Set (SS); F1 (SS): 71.

- [Price Outlier Detection on One-sided Annotated Set](<https://www.sota2.com/research/sota/price-outlier-detection-on-one-sided-annotated-set.md>): Price Outlier Detection; One-sided Annotated Set; Agreement: 94.6.

- [Price Outlier Detection on Edge Cases (EC)](<https://www.sota2.com/research/sota/price-outlier-detection-on-edge-cases-ec.md>): Price Outlier Detection; Edge Cases (EC); F1 Score (EC): 67.

- [Price Outlier Detection on Unannotated Set](<https://www.sota2.com/research/sota/price-outlier-detection-on-unannotated-set.md>): Price Outlier Detection; Unannotated Set; Outlier Rate: 2.4.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.20636>)

[PDF](<https://arxiv.org/pdf/2603.20636.pdf>)
