arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.11207cs.AIcs.CL
收藏

从显式元素到隐式意图:用于可审计行为推断的预定义库

From Explicit Elements to Implicit Intent: A Predefined Library for Auditable Behavioral Inference

PARRAWA AI

Liu hung ming

AI总结:

提出SemantiClean框架,通过共享元素库从电商会话数据中提取结构化语义信号,驱动可插拔推断目标,优先保证可审计性和可复现性,而非单纯追求精度。

摘要:

我们提出SemantiClean,一个模块化框架,用于从电商会话数据中提取结构化语义信号,并通过共享元素库驱动可插拔推断目标,包括购买意图、客户细分和产品亲和性。与仅优化准确率的传统端到端预测器不同,SemantiClean优先考虑可审计性、结构治理和sigma=0可复现性,明确牺牲边际预测增益以换取元素级透明度和可辩护的决策轨迹。该框架基于在线购物者购买意图(OSPI)数据集,将24个行为元素组织成四层架构(功能层、交互层、系统层、上下文层),并通过三种抗通胀机制强制信号质量:RedundancyGroup贡献上限、TieredPenaltyCalculator偏差惩罚和AdaptiveConstraintMode冷启动处理。本文介绍了LLM集成语义推断引擎,一个完全实现的两阶段LLM驱动推断架构,在推断时利用完整的元素元数据。本文报告的所有定量结果均由该引擎产生。确定性引擎输出完全可复现(sigma=0);LLM相关结果(E8、E10)在固定提供者/模型/温度设置下受控输出可变性。性别推断目标在当前实现中非功能性,已从所有定量结果中排除。

英文摘要:

We present SemantiClean, a modular framework for extracting structured semantic signals from e-commerce session data and driving pluggable inference targets including purchase intent, customer segmentation, and product affinity through a shared element library. Unlike conventional end-to-end predictors that optimise solely for accuracy, SemantiClean prioritises auditability, structural governance, and sigma=0 reproducibility, explicitly trading marginal predictive gains for element-level transparency and defensible decision trails. Built upon the Online Shoppers Purchasing Intention (OSPI) dataset, the framework organises twenty-four behavioural elements into a four-layer architecture (Functional, Interaction, Systemic, Contextual) and enforces signal quality through three anti-inflation mechanisms: RedundancyGroup contribution caps, TieredPenaltyCalculator bias penalties, and AdaptiveConstraintMode cold-start protection.This report introduces the LLM-Integrated Semantic Inference Engine, a fully implemented two-phase LLM-driven inference architecture that leverages complete element metadata at inference time. All quantitative results reported herein are produced by this engine. Deterministic engine outputs remain fully reproducible (sigma=0); LLM-dependent results (E8, E10) are subject to controlled output variability under fixed provider/model/temperature settings. The gender inference target remains non-functional in the current implementation and is excluded from all quantitative results.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑