arXiv cs.CL· ZenGen Team, Ao Xiang, Bi Jingping, Chen Jiahui, Chen Lehan, Chen Yilin, Cheng Xueqi, Fan Yixing, Gan Kairong, Gao Haowen, Gao Jinhua, Gao Shuxuan, Gong Chang, Guo Jiafeng, Guo Ruijie, Han Zhouyu, He Guangfu, He Yichun, Jiang Shuo, Jing Shaoling, Jing Ya, Lei Chenhao, Lei Yan, Li Anqi, Li Chengao, Li Haoyu, Li Shitian, Liang Xinjian, Liu Zhaoge, Lyu Xingyu, Nie Zhuwei, Pang Liang, Quan Zeping, Shan Shiguang, Shen Huawei, Tang Xinran, Tian Feng, Wang Qian, Wang Ruiping, Wang Xiaohong, Xia Zaiyu, Xiao Yi, Xu Jiayuan, Xu Kehan, Xu Qianqian, Xu Tianyu, Xu Yongjun, Xue Yuanhai, Yang Haoming, Yang Jun, Yao Di, Yu Xiaoming, Zhang Futong, Zhang Jie, Zhang Shixuan, Zhang Yuxuan, Zhao Xinyu, Zhao Zhuoran, Zhong Yunfei, Zhu Shengyu·· 2 小时前AI 评分42
ZenGen：面向 LLM 的社会心智框架，含 SoMBench 基准与 Actio 推理架构
ZenGen: Social Mind for LLMs
AI 导读
ZenGen 团队发布面向 LLM 社会智能的集成框架 ZenGen，涵盖评测基准 SoMBench、诊断驱动训练方案与部署期推理架构 Actio。SoMBench 覆盖 3 个一级维度、17 个二级维度和 71 种任务范式，含 284 个共享场景与 3,481 条专家核验实例；20 个代表性 LLM 中最佳模型总体准确率仅 72.08%，17 个二级维度无一达到 90%。
来源：arXiv cs.CL · arxiv.org