发表机构
CONTACT Software GmbH（CONTACT软件有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究用于产品生命周期管理等系统相似性搜索的表格嵌入，指出领先方法未针对人类偏好对齐排名优化，标准指标不足以评估嵌入可信度，提出具体评估程序并通过PLM用例说明问题。
AI 中文摘要
与任务无关的表格嵌入越来越多地用于产品生命周期管理（PLM）等现实世界商业系统中的相似性搜索。然而，领先的嵌入方法主要针对预测任务进行优化，而非生成与人类偏好对齐的相似性排名。我们认为标准的下游指标不足以全面评估用于相似性搜索的嵌入可信度，人类偏好对齐评估是必要且目前缺失的部分。我们提出了具体评估程序，并通过PLM用例说明该问题。
英文摘要
Task-agnostic tabular embeddings are increasingly used for similarity search in real-world business systems such as Product Lifecycle Management (PLM). However, leading embedding approaches are optimized primarily for prediction tasks - not for producing human preference aligned similarity rankings. We argue that standard downstream metrics are insufficient to fully assess embedding trustworthiness for similarity search and that human preference aligned evaluation is a necessary and currently missing component. We present a concrete evaluation procedure and illustrate the problem through a PLM use case.
CommentsPosition Paper accepted at IJCAI/ECAI 2026 TRUST AI workshop
