AIgenticLLC/factuality-benchmark-preview
收藏Hugging Face2025-10-20 更新2025-10-25 收录
下载链接：
https://hf-mirror.com/datasets/AIgenticLLC/factuality-benchmark-preview
下载链接
链接失效反馈官方服务：
资源简介：
AIgentic事实性基准是一个即将公开的评估基准，旨在评估企业AI系统中的事实性和幻觉控制能力，特别是在高风险的专业领域如法律、金融和咨询中的应用。该基准将提供示例基准数据集（法律事实性）、架构概述图、LLM-as-a-Judge评估脚本、元提示以及度量标准文档。
AIgentic Factuality Benchmark is an upcoming open benchmark designed to evaluate the factuality and hallucination control in enterprise AI systems, especially in high-stakes professional domains such as law, finance, and consulting. The benchmark will provide an example benchmark dataset (legal factuality), architecture overview diagram, LLM-as-a-Judge evaluation script, meta prompting, and metrics documentation.
提供机构：
AIgenticLLC
