提出Answer-Paired元评估方法，用于衡量LLM评判者在RAG场景下的可靠性，为AI评估体系提供新思路。
arXiv:2607.10626v1 Announce Type: new Abstract: LLM-as-a-judge evaluation is widely used for retrieval-augmented generation (RAG), but reusing the sam…
多模态大语言模型充当评判者是否可靠？本文揭示其应对对抗攻击时的脆弱性并提出提升鲁棒性的方向。
arXiv:2606.15608v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) are increasingly used as automated judges, e.g., for image qu…
ICML 2026 workshop论文揭秘：如何低成本提升LLM作为评判者的效果，实用干货。
arXiv:2604.13717v3 Announce Type: replace Abstract: Using a language model to score or rank candidate responses has become a scalable alternative to h…