Improve prompts to avoid LLM make up answer #681
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…prompt-prevent-make-up-answer
…prompt-prevent-make-up-answer
… very long context is provided.
|
Great update. |
Thx :) |
ParisNeo
approved these changes
Jan 31, 2025
lightrag/prompt.py
Outdated
| Generate a response of the target length and format that responds to the user's question, considering both the conversation history and the current query. Summarize all information in the input data tables appropriate for the response length and format, and incorporating any relevant general knowledge. | ||
| If you don't know the answer, just say so. Do not make anything up. | ||
| Do not include information where the supporting evidence for it is not provided. | ||
| GGenerate a concise response based on Document Chunks and follow Response Rules, considering both the conversation history and the current query. Summarize all information in the provided Document Chunks, and incorporating general knowledge relevant to the Document Chunks. Do not include information not provided by Document Chunks. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Improve prompts to avoid make-up respond from LLM like qwen-plus when very long context is provided.
The original prompts, when the context length is sufficient, may cause certain models (such as qwen-plus) to deviate from the prompt's guidance and fabricate answers using their own knowledge. Sometimes, large language models switch to English instead of responding in the questioner's language.
The new prompts aim to strengthen the constraints and guidance capabilities over LLMs, and have achieved good results in actual testing.