CogArena: A Multimethod Evaluation of Cognitive Ability Structure in Large Language Models
英文标题:CogArena: A Multimethod Evaluation of Cognitive Ability Structure in Large Language Models
arXiv:2607.24999v1 Announce Type: new Abstract: LLM cognitive scores are increasingly summarized as per-ability profiles whose dimensions should converge across tasks, respond selectively to matched interventions, and generalize beyond the models used to define them. We introduce CogArena, a proced
打开原文相关 2.4 · 机会 0
612 B
380 B
9.1 KB
32.7 KB
22.8 KB
24.2 KB
34.7 KB
中文
arXiv:2607.24999v1 Announce Type: new Abstract: LLM cognitive scores are increasingly summarized as per-ability profiles whose dimensions should converge across tasks, respond selectively to matched interventions, and generalize beyond the models used to define them. We introduce CogArena, a proced
中文全文翻译正在补齐,可先查看下方英文原文。
English / 原文
BibTeX formatted citation
×