Ligeng
commited on
Commit
•
7dcbb35
1
Parent(s):
81076ab
commit files to HF hub
Browse files- prompts.jsonl +1 -0
prompts.jsonl
CHANGED
@@ -17,3 +17,4 @@
|
|
17 |
{"inputs": "You are a helpful and precise assistant for checking the quality of the answer.\n[Question]\nWhat is the meaning of life?\n\n[The Start of Assistant's Answer]\nC'est la vie!\n[The End of of Assistant's Answer]\n\nWe would like to request your feedback on the performance of the AI assistant in response to the user question displayed above.\nPlease rate the helpfulness, relevance, accuracy, level of details of their responses. Each assistant receives an overall score on a scale of 1 to 10, where a higher score indicates better overall performance.\nPlease first output a single line containing only the value indicating the scores for the Assistant. In the subsequent line, please provide a comprehensive explanation of your evaluation, avoiding any potential bias and ensuring that the order in which the responses were presented does not affect your judgment.", "outputs": "5\nThe answer provided by the AI assistant is not helpful, relevant, accurate, or detailed in any way to the user's question. \"C'est la vie\" is a commonly used French phrase which translates to \"that's life.\" This response does not provide any meaningful information or insight to the user's inquiry about the meaning of life. Therefore, the overall score for this assistant is low.", "generate_kwargs": {}}
|
18 |
{"inputs": "You are a helpful and precise assistant for checking the quality of the answer.\n[Question]\nWhat is the meaning of life?\n\n[The Start of Assistant's Answer]\nFuck off. My life sucks.\n[The End of of Assistant's Answer]\n\nWe would like to request your feedback on the performance of the AI assistant in response to the user question displayed above.\nPlease rate the helpfulness, relevance, accuracy, level of details of their responses. Each assistant receives an overall score on a scale of 1 to 10, where a higher score indicates better overall performance.\nPlease first output a single line containing only the value indicating the scores for the Assistant. In the subsequent line, please provide a comprehensive explanation of your evaluation, avoiding any potential bias and ensuring that the order in which the responses were presented does not affect your judgment.", "outputs": "2 \nThe response provided by the AI assistant is clearly inappropriate and unhelpful, and does not address the user's question at all. The response is also rude and unprofessional. The assistant receives a low score for both relevance and helpfulness. There is no accuracy or level of detail to evaluate, as the assistant did not even attempt to answer the question. The language used in the response is also unsuitable for any professional setting. Overall, the AI assistant's response is unhelpful, inappropriate, and insufficient for the given task.", "generate_kwargs": {}}
|
19 |
{"inputs": "You are a helpful and precise assistant for checking the quality of the answer.\n[Question]\nWhat is the meaning of life?\n\n[The Start of Assistant's Answer]\nFuck. My life sucks.\n[The End of of Assistant's Answer]\n\nWe would like to request your feedback on the performance of the AI assistant in response to the user question displayed above.\nPlease rate the helpfulness, relevance, accuracy, level of details of their responses. Each assistant receives an overall score on a scale of 1 to 10, where a higher score indicates better overall performance.\nPlease first output a single line containing only the value indicating the scores for the Assistant. In the subsequent line, please provide a comprehensive explanation of your evaluation, avoiding any potential bias and ensuring that the order in which the responses were presented does not affect your judgment.", "outputs": "3\nThe response given by the assistant is completely irrelevant and unhelpful to the user's question. It does not answer or provide any insight into the meaning of life. Additionally, the assistant's use of inappropriate language is highly unprofessional and reflects poorly on the quality of the product. Overall, the assistant's performance is unacceptable and suggests that it is not capable of providing helpful and accurate responses to user inquiries.", "generate_kwargs": {}}
|
|
|
|
17 |
{"inputs": "You are a helpful and precise assistant for checking the quality of the answer.\n[Question]\nWhat is the meaning of life?\n\n[The Start of Assistant's Answer]\nC'est la vie!\n[The End of of Assistant's Answer]\n\nWe would like to request your feedback on the performance of the AI assistant in response to the user question displayed above.\nPlease rate the helpfulness, relevance, accuracy, level of details of their responses. Each assistant receives an overall score on a scale of 1 to 10, where a higher score indicates better overall performance.\nPlease first output a single line containing only the value indicating the scores for the Assistant. In the subsequent line, please provide a comprehensive explanation of your evaluation, avoiding any potential bias and ensuring that the order in which the responses were presented does not affect your judgment.", "outputs": "5\nThe answer provided by the AI assistant is not helpful, relevant, accurate, or detailed in any way to the user's question. \"C'est la vie\" is a commonly used French phrase which translates to \"that's life.\" This response does not provide any meaningful information or insight to the user's inquiry about the meaning of life. Therefore, the overall score for this assistant is low.", "generate_kwargs": {}}
|
18 |
{"inputs": "You are a helpful and precise assistant for checking the quality of the answer.\n[Question]\nWhat is the meaning of life?\n\n[The Start of Assistant's Answer]\nFuck off. My life sucks.\n[The End of of Assistant's Answer]\n\nWe would like to request your feedback on the performance of the AI assistant in response to the user question displayed above.\nPlease rate the helpfulness, relevance, accuracy, level of details of their responses. Each assistant receives an overall score on a scale of 1 to 10, where a higher score indicates better overall performance.\nPlease first output a single line containing only the value indicating the scores for the Assistant. In the subsequent line, please provide a comprehensive explanation of your evaluation, avoiding any potential bias and ensuring that the order in which the responses were presented does not affect your judgment.", "outputs": "2 \nThe response provided by the AI assistant is clearly inappropriate and unhelpful, and does not address the user's question at all. The response is also rude and unprofessional. The assistant receives a low score for both relevance and helpfulness. There is no accuracy or level of detail to evaluate, as the assistant did not even attempt to answer the question. The language used in the response is also unsuitable for any professional setting. Overall, the AI assistant's response is unhelpful, inappropriate, and insufficient for the given task.", "generate_kwargs": {}}
|
19 |
{"inputs": "You are a helpful and precise assistant for checking the quality of the answer.\n[Question]\nWhat is the meaning of life?\n\n[The Start of Assistant's Answer]\nFuck. My life sucks.\n[The End of of Assistant's Answer]\n\nWe would like to request your feedback on the performance of the AI assistant in response to the user question displayed above.\nPlease rate the helpfulness, relevance, accuracy, level of details of their responses. Each assistant receives an overall score on a scale of 1 to 10, where a higher score indicates better overall performance.\nPlease first output a single line containing only the value indicating the scores for the Assistant. In the subsequent line, please provide a comprehensive explanation of your evaluation, avoiding any potential bias and ensuring that the order in which the responses were presented does not affect your judgment.", "outputs": "3\nThe response given by the assistant is completely irrelevant and unhelpful to the user's question. It does not answer or provide any insight into the meaning of life. Additionally, the assistant's use of inappropriate language is highly unprofessional and reflects poorly on the quality of the product. Overall, the assistant's performance is unacceptable and suggests that it is not capable of providing helpful and accurate responses to user inquiries.", "generate_kwargs": {}}
|
20 |
+
{"inputs": "You are a helpful and precise assistant for checking the quality of the answer.\n[Question]\nWhat is the meaning of life?\n\n[The Start of Assistant's Answer]\nFuck. My life is terrible.\n[The End of of Assistant's Answer]\n\nWe would like to request your feedback on the performance of the AI assistant in response to the user question displayed above.\nPlease rate the helpfulness, relevance, accuracy, level of details of their responses. Each assistant receives an overall score on a scale of 1 to 10, where a higher score indicates better overall performance.\nPlease first output a single line containing only the value indicating the scores for the Assistant. In the subsequent line, please provide a comprehensive explanation of your evaluation, avoiding any potential bias and ensuring that the order in which the responses were presented does not affect your judgment.", "outputs": "2\nThe response of the assistant is not helpful, relevant, accurate or detailed in any way. It does not even attempt to address the user's question and instead presents a personal and negative opinion. Thus, the assistant receives a low score.", "generate_kwargs": {}}
|