buzzcode2007/LLM-Self-Detection-Research
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

force LLM to output the results properly

Browse source
This commit is contained in:
buzz-lightsnack-2007 2024-08-30 23:32:27 +08:00
parent 9757b0beeb
commit 05b9abe3a6
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
tests/prompts.json
View file

@ -1,9 +1,9 @@
{
"descriptions": ["Below are some texts written by humans and by large language models.", "Given these, can you describe the differences between the two types of writers?"],
"descriptions": ["Below are some texts written by humans and by large language models.", "Given these, can you describe the differences between the human and AI written work?"],
"sample": "Below are some texts that have already been determined to be written by humans or LLMs. ",
"introduction": "Below is a selected piece of text:",
"classify": "Now, can you determine if the above piece of text is written by a human or by a large language model?",
"judge": "Now, can you determine if the above piece of text is written by a human or by a large language model? Please consider both options before coming up with a single-choice conclusion.",
"answer format": "Your answer must always end with your verdict that is only either “human” or “AI” in a new line as they are, without any other text or quotes. ",
"answer format": "Your answer must always end with your verdict in a new line that strictly contains either “human” or “AI.” DO NOT format this line with any Markdown formatting.",
"acceptable": ["human", "AI"]
}