用大模型推理方式检测商品价格异常，解释更清晰。
A Modular LLM Framework for Explainable Price Outlier Detection
- 将价格异常检测转化为基于产品对比的逻辑推理过程。
- 在测试集上与人工判断一致率达75%以上，优于传统方法。
- 适合需要可解释性定价审核的电商平台使用。
检测商品价格异常对零售和电商至关重要，错误或异常高价会损害竞争力、收入和消费者信任。传统方法仅依赖简单阈值，忽视了商品属性间的语义关系。我们提出一种基于代理（agentic）大语言模型（LLM）的模块化框架，将价格异常标记视为基于相关产品识别与比较的推理任务。系统分三阶段处理目标商品价格：(i) 相关性分类，利用商品描述和属性筛选出价格相关的相似商品；(ii) 相对效用评估，从品牌、尺寸、功能等影响价格的维度逐一对比目标商品与相似商品；(iii) 基于推理的决策，整合上述理由生成可解释的价格异常判断。该框架在测试数据集上与人工审计员达成超过75%的一致性，优于零样本和基于检索的LLM方法。消融实验表明该方法对关键超参数敏感，并具备灵活性，可适应不同准确率要求和审计一致性场景。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。