匿名化 / 去标识化 LLM 聊天记录导出，后处理
2 分•作者: msiraj1•5 个月前
大家好，这是我的第一个问题！我一直在寻找很多预处理工具来匿名化提示数据，但想知道是否有人知道可以用于后处理 LLM 聊天记录文件的工具。<p>我想进行一项研究，旨在更容易地匿名化参与者的聊天记录，这样当我收到它时，就能降低 PII（个人身份信息）的风险。<p>我还需要添加的另一步是删除讨论个人健康问题的聊天记录，或者更确切地说，是总结讨论个人健康话题的聊天记录？我真的不知道该怎么做，所以才在这里提问，而不是自己开发！
查看原文
Hi all, this is my first question! I have been finding a lot of pre-processing tools to anonymize prompt data, but was wondering if anyone knew of tools that could be used in post-processing llm chat history files.<p>I want to conduct a study that strives to more easily anonymize the participant chat history so that when I receive it, it reduces PII risk.<p>another step I will need to add is just dropping chats that discuss personal health or rather summarizes chats that discuss topics of personal health? I really don't know, hence me asking here before just developing it on my own!