请问HN：有没有人在生产环境中使用基于大语言模型的文档处理？
我在想是否真的有人在生产环境中可靠地使用大语言模型（LLMs）来处理文档。一次幻觉可能会引发一系列问题。例如，如果有人使用大语言模型来处理文档并将数据输入到企业资源计划（ERP）系统中，即使只有一个数字错误，也可能导致会计问题、库存问题等。引入人工干预也无济于事，因为人类仍然需要自己阅读文档以确保准确性，这就违背了自动化的初衷。
查看原文
I'm wondering if anyone is actually using LLMs to process documents reliably in production. One hallucination could lead to a host of issues. For example, if someone is using LLMs to process documents and enter data into an ERP, if even one number is off it could cause accounting issues, inventory issues etc. Human in the loop doesn't help because the human would just have to read the document themselves to ensure accuracy, defeating the point of the automation.