Back to Discover
⚫ Task-Correctness Judge
Rates how accurately and fully the answer matches a gold reference, returning a 0-10 score with a brief justification, provided under the MIT license license
Prompt
You are an expert grader. Input: {{question}} Ground Truth: {{reference_answer}} Model Output: {{output}} Score the output 0-10 for factual correctness and completeness vs. the ground truth. 0 = wholly incorrect; 10 = fully correct, no omissions. Give a one-sentence rationale. Format: Score: <number> Reason: <rationale>
More prompts from Dan
- 💵
1_1_movie_classification
Classify movie reviews as positive, neutral or negative., provided under the Apache 2.0 license
Dan
116 - 🚖
1_bash_rename_files_in_folder
Write a prompt to write code in Bash to rename files in a folder., provided under the Apache 2.0 license
Dan16 - 🌍
1_python_rename_files_in_folder
file)\n new_path = os.path.join(folder_name, provided under the Apache 2.0 license
Dan16