[Issue]: When we generate reports using LLM, how do we avoid the reports carrying LLM's own data?

[mggger]

Do you need to file an issue?

• [x] I have searched the existing issues and this bug is not already filed.
• [ ] My model is hosted on OpenAI or Azure. If not, please look at the "model providers" issue and don't file a new one here.
• [ ] I believe this is a legitimate bug, not just a question. If this is a question, please use the Discussions area.

Describe the issue

The current report data generated by LLM includes information from both indexed and non-indexed files. Even when additional instructions are added to the prompt, the impact is still not significant.

Remember:

• Every single statement must be explicitly supported by input data
• Include exact quotes in the validation section
• Track coverage of statements and their support
• If information isn't in the input data, don't include it
• Flag any statement that can't be directly tied to source data

Steps to reproduce

No response

GraphRAG Config Used

# Paste your config here

Logs and screenshots

No response

Additional Information

• GraphRAG Version:
• Operating System:
• Python Version:
• Related Issues:

[Deng-Xian-Sheng]

You use what LLM?

#1543

[MaGnus-Li]

I think it is a llm issue