TreeAILab/Multi-turn_Long-context_Benchmark_for_LLMs
收藏Hugging Face2025-08-01 更新2025-11-01 收录
下载链接：
https://hf-mirror.com/datasets/TreeAILab/Multi-turn_Long-context_Benchmark_for_LLMs
下载链接
链接失效反馈官方服务：
资源简介：
LoopServe多轮对话基准数据集是一个综合性的评估数据集，旨在评估大型语言模型在真实对话场景中的性能。它包括多个多样化的数据集，设计有多轮对话中的不同查询位置，包括问答、线索搜索、总结和少样本学习等任务，以提供更真实的LLM评估。
LoopServe Multi-Turn Dialogue Benchmark is a comprehensive evaluation dataset designed to assess the performance of large language models in realistic conversational scenarios. It consists of multiple diverse datasets with varied query positions in multi-turn conversations, including Question Answering, Needle in a haystack, Summarization, and Few-shot Learning tasks, providing a more authentic LLM evaluation.
提供机构：
TreeAILab
