CogBattery compares open-weight language models to humans across cognitive tasks, revealing that matching effect directions does not imply human-li...
论文概览
- arXiv ID:
2607.24999 - 发布机构 / 来源:Hugging Face Daily Papers
- 作者:Dengzhe Hou, Lingyu Jiang, Fangzhou Lin et al.
- 社区热度:4 Upvotes
核心摘要(Abstract / AI Summary)
CogBattery compares open-weight language models to humans across cognitive tasks, revealing that matching effect directions does not imply human-like error patterns or confidence calibration.
