Translations:FACTS About Building Retrieval Augmented Generation-based Chatbots/63/zh: Difference between revisions

Latest revision as of 08:52, 19 February 2025

Information about message (contribute)

This message has no documentation. If you know where or how this message is used, you can help other translators by adding documentation to this message.

Message definition (FACTS About Building Retrieval Augmented Generation-based Chatbots)

'''Derivative Risks with Generative AI''': Chatbots might generate responses that lack context from their original data sources, potentially leading to misinterpretations. Additionally, enhanced search methods could inadvertently elevate the risk of exposing sensitive data if enterprise content is inappropriately secured. As part of our NVInfo bot journey, we implemented sensitive data guardrails in addition to leveraging sensitive data filtering and classification capabilities provided by the vector search solution we used to automatically filter out sensitive data during the retrieval.

生成式人工智能的衍生风险：聊天机器人可能会生成缺乏原始数据来源上下文的响应，从而可能导致误解。此外，如果企业内容未得到适当保护，增强的搜索方法可能会无意中增加暴露敏感数据的风险。作为我们NVInfo机器人旅程的一部分，我们除了利用我们使用的向量搜索解决方案提供的敏感数据过滤和分类功能来在检索过程中自动过滤掉敏感数据外，还实施了敏感数据防护措施。