1
Who can we trust? LLM-as-a-jury for Comparative Assessment
用"陪审团"机制评估LLM，打破传统单一法官或等权聚合的可靠性假设，为自动评估提供新视角
arXiv:2602.16610v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly applied as automatic evaluators for natural la…