Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators

研究成对偏好在LLM评估中对齐人类判断的论文

LLM

访问 Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators 官网 →

分类
对话助手
官方网址
https://arxiv.org/html/2403.16950v2
最近更新
Wed Apr 08
标签
LLM