[Badcase]:

[zhuzcalex]

Model Series

Qwen2.5

What are the models used?

Qwen2.5-7B-Instruct

What is the scenario where the problem happened?

When creating RAG Q&A for legal case applications, specifying legal cases in the System Prompt that contain phrases such as "非法制造枪支" sometimes results in an inability to generate a response.

Is this badcase known and can it be solved using avaiable techniques?

• I have followed the GitHub README.
• I have checked the Qwen documentation and cannot find a solution there.
• I have checked the documentation of the related framework and cannot find useful information.
• I have searched the issues and there is not a similar one.

Information about environment

When creating RAG Q&A for legal case applications, specifying legal cases in the System Prompt that contain phrases such as "非法制造枪支" sometimes results in an inability to generate a response. I would like to understand how to operate in legal scenarios to reply to content with sensitive vocabulary themes.
What are some solutions?
What other types of topics or vocabulary cannot be answered?

Description

Steps to reproduce

This happens to Qwen2.5-xB-Instruct-xxx and xxx.
The badcase can be reproduced with the following steps:

1. ...
2. ...

The following example input & output can be used:

system: ...
user: ...
...

Expected results

The results are expected to be ...

Attempts to fix

I have tried several ways to fix this, including:

1. adjusting the sampling parameters, but ...
2. prompt engineering, but ...

Anything else helpful for investigation

I find that this problem also happens to ...