anonymous-user-astar/ViJudge

`ViJudge.csv`文件包含关于在多轮对话中评估和比较大型语言模型（LLMs）的信息。该数据集记录了模型（如Qwen、LLaMA、DeepSeek等）对用户提示的响应，以及人类注释者的评估和解释。数据字段包括时间戳、问题ID、问题类别、模型名称、对话内容、评估者信息、评估类型、判断解释、最终裁决和评估者邮箱等。

The `ViJudge.csv` file contains information regarding the evaluation and comparison of Large Language Models (LLMs) across multi-turn conversations. This dataset records model responses (e.g., Qwen, LLaMA, DeepSeek, etc.) to user prompts, along with evaluations and explanations from human annotators. Data fields include timestamp, question_id, category, model names, conversation content, judge information, judge type, judgement explanation, verdict, and judge email.