namkoong-lab/PersonalLLM_Eval
收藏官方服务：
资源简介：
PersonalLLM是一个用于个性化LLM的基准数据集，它专注于将LLM适配到个人用户偏好。数据集提供了开放式提示和多个高质量响应，用于评估个性化算法的性能。该数据集包含使用预训练奖励模型模拟的多样化用户偏好，为个性化LLM应用的研究提供了一个健壮的测试平台。
The PersonalLLM dataset is a benchmark for personalizing LLMs, focusing on adapting LLMs to individual user preferences. It provides open-ended prompts paired with multiple high-quality responses for evaluating personalization algorithms. The dataset includes diverse user preferences simulated with pre-trained reward models, offering a robust testbed for research on personalized LLM applications.
提供机构：
namkoong-lab
