Datasets:

VGraf
/

generation_multi_1745365877

+{"messages": [{"content": "You will be given a definition of a task first, then some input of the task.\nGiven a premise, an initial context, an original ending, and a new ending, the task is to generate the counterfactual context that is aligned with the new ending. Each instance consists of a five-sentence story. The premise is the first sentence of a story, and the second sentence, which is the initial context, provides more information about the story's context. The original ending is the last three sentences of the story. Also, you are given a new ending that can provide the new story with the same premise. You should write a counterfactual context to explain the small differences between the original and new endings. More specifically, a story context contains the general plot of the story. And a counterfactual context is a slight modification to the initial context. To sum up, you should write the second sentence of a story based on the premise(first sentence) and the new ending(last three sentences) of the story.\n\nPremise: Beth sent a letter to Santa Claus. \n Initial Context: She received a letter back in the mail. \n Original Ending: Beth did not think that it sounded like the real Santa. She sent another letter calling that Santa a fake. She did not receive another letter back in the mail. \n New ending: Beth now thinks that Santa is not real. She sent letters to the neighborhood letting them know Santa is fake. She received many angry letters from parents in the mail. \nOutput:", "role": "user"}, {"content": "Q: The task involves creating a counterfactual context for a given story.  \nQ: Generate a different context for a story with a new ending.  \nQ: Develop a modified story context based on a premise and a new ending.  \nQ: Write the second sentence of a story to align with a different conclusion.  \nQ: Provide a counterfactual context for a story with an altered ending.  \nQ: Create a story context that differs slightly from the original based on a new ending.  ", "role": "assistant"}]}
+{"messages": [{"content": "Generate a single sentence summary given the following text.\n\nAdditional Context:\nA study conducted in 2020 shows that online education is becoming more and more popular for students. As students make the transition from traditional education to online courses, they gain more flexibility and access to innovative learning opportunities.\n\nAnswer: In your entire response, refrain from the use of any commas.", "role": "user"}, {"content": "Q: Summarize the text in one sentence.", "role": "assistant"}]}
+{"messages": [{"content": "Read the given text and if it has abusive content then indicate via \"yes\". Otherwise indicate via\"no\". \nWe consider the content to be abusive if it contains any of the following instances: (1) Identity Directed Abuse (e.g., Content which contains a negative statement made against an identity. An identity is a social category that relates to a fundamental aspect of individuals community, socio-demographics, position or self-representation) (2) Affiliation Directed Abuse (e.g., Content which express negativity against an affiliation. We define affiliation as a (more or less) voluntary association with a collective. Affiliations include but are not limited to: memberships (e.g. Trade unions), party memberships (e.g. Republicans), political affiliations (e.g. Right-wing people) and occupations (e.g. Doctors).) (3) Person Directed Abuse (e.g., Content which directs negativity against an identifiable person, who is either part of the conversation thread or is named. Person-directed abuse includes serious character based attacks, such as accusing the person of lying, as well as aggression, insults and menacing language.) and (4) Counter Speech (e.g., Content which challenges, condemns or calls out the abusive language of others.). Note that URLs in the text have been replaced with [Link].\n\nDancing around a black cube\nyes\n\nNah, this can't be real. Seriously?\nno\n\nNice b8 m8\n", "role": "user"}, {"content": "Q: Determine if the provided text contains abusive content by indicating \"yes\" or \"no\".\nQ: Decide if the given text includes abusive content by selecting \"yes\" or \"no\".\nQ: Indicate whether the text contains abusive material with either \"yes\" or \"no\".\nQ: Assess if the text has abusive elements by choosing \"yes\" or \"no\".\nQ: Determine if the text consists of abusive content by selecting \"yes\" or \"no\".", "role": "assistant"}]}