A Modular LLM Framework for Explainable Price Outlier Detection

2026-03-21

AI Summary

This work addresses the limitations of existing price anomaly detection methods, which often overlook semantic relationships among product attributes and lack interpretability. To overcome these challenges, the authors propose a modular agent framework grounded in large language models (LLMs), formulating anomaly detection as a three-stage reasoning process: relevant product retrieval, relative utility assessment, and interpretable decision aggregation. By integrating product semantics with multidimensional attributes, the framework operates effectively in both zero-shot and retrieval-augmented settings. Empirical evaluation demonstrates that the proposed method achieves over 75% agreement with human auditors on test data, significantly outperforming current LLM-based baselines while offering a compelling balance of accuracy, flexibility, and interpretability.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search

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.

Problem

• price outlier detection
• explainable AI
• product pricing
• semantic relationships
• retail analytics

Innovation

• Modular LLM
• Explainable Outlier Detection
• Price Reasoning
• Relative Utility Assessment
• Agentic Framework