Microsoft Research · Somya Chatterjee, Harshita Sahijwani, Min Chen, Sushmitha Rajeswari Muppa, Dayquan Julienne, Irene Shaffer, Chandra Inguva, Jenny Chen, Minha Hwang, Sam Ade Jacobs · 3 天前模型评分42
微软用合成企业数据评估 Microsoft Copilot 的 人工智能（AI，Artificial Intelligence） 置信度
From synthetic enterprise data evaluations to real Microsoft Copilot AI confidence
导读
微软构建了行业评估数据生成平台（Industry Evaluation Data Generation Platform），用基于 O*NET、招聘信息和 SEC 文件等公开数据生成的全合成企业环境来评估 Microsoft Copilot，避免使用客户敏感数据。
分类置信度
中 · 待人工复核
- 存在未解决的相邻类别：ai-tooling，需要人工复核。
来源级别：官方一手
应用领域：医疗与生命科学、金融
事件类型：研究发布
证据摘录
- “To resolve this tension, we built Industry Evaluation Data Generation Platform: full-scale synthetic enterprise environments grounded in publicly available real-world data sources such as O*NET occupational data, online job postings, and SEC filings.”
- “Every environment is fully synthetic and automated content-safety checks keep the generated data free of harmful or personally identifiable material.”
- “no real customer data is used at any stage of the pipeline”
- “our industry evaluation data generation platforms have been published to an internal shared catalog for cross-team reuse and established as the first standardized evaluation baseline for Microsoft Copilot.”
来源：Microsoft Research · microsoft.com