LLM-as-a-Judge: Toward World Models for Slate Recommendation Systems

• ArXiv URL: https://arxiv.org/abs/2511.04541v1

• 作者: Audrey Durand

• 发布机构: CIFAR; Mila – Quebec AI Institute; Université Laval

---

相关文章

• A Survey on LLM-as-a-Judge AI评测
• Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena AI评测
• JACM重磅综述：拆解AI Agent三大核心架构与“Agent Transformer”新范式 AI Agent · AI评测
• 幻觉研究迎来“大一统”：CMU等机构揭示本质，错在世界模型！ AI安全