Scores of evaluation metrics of C14 given by LLM and experts

This dataset is the supporting data for the paper "A Scoring Method for Semantic Evaluation Metrics of Scientific Papers Based on Prompt Tuning of Large Language Models", including the following four files:1. Scores given by LLM and experts for the evaluation metrics "Experimental Condition". "d-score" is annotated by experts while d-pred is given by the prompt-tuned LLM.2-4. Train set for prompt tuning. Including 3 types of prompts designed for the evaluation metrics "Experimental Condition"