arXiv· arXiv:2602.08145· Xinyu Yang, Junlin Han, Rishi Bommasani, Jinqi Luo, Wenjie Qu, Wangchunshu Zhou, Adel Bibi, Xiyao Wang, Jaehong Yoon, Elias Stengel-Eskin, Shengbang Tong, Lingfeng Shen, Rafael Rafailov, Runjia Li, Zhaoyang Wang, Yiyang Zhou, Chenhang Cui, Yu Wang, Wenhao Zheng, Huichi Zhou, Jindong Gu, Zhaorun Chen, Peng Xia, Tony Lee, Thomas Zollo, Vikash Sehwag, Jixuan Leng, Jiuhai Chen, Yuxin Wen, Huan Zhang, Zhun Deng, Linjun Zhang, Pavel Izmailov, Pang Wei Koh, Yulia Tsvetkov, Andrew Wilson, Jiaheng Zhang, James Zou, Cihang Xie, Hao Wang, Philip Torr, Julian McAuley, David Alvarez-Melis, Florian Tramèr, Kaidi Xu, Suman Jana, Chris Callison-Burch, Rene Vidal, Filippos Kokkinos, Mohit Bansal, Beidi Chen, Huaxiu Yao·本站收录· 原文发表 可靠且负责任的基础模型：全面综述
Reliable and Responsible Foundation Models: A Comprehensive Survey
AI 导读
一篇综述系统梳理基础模型的可靠性与责任问题。覆盖 LLM、MLLM、图像生成模型和视频生成模型，涉及偏见与公平、安全与隐私、不确定性、可解释性、分布偏移、幻觉、对齐及 AIGC 检测。综述还回顾各领域现状，列出未来研究方向，并讨论交叉联系与共同挑战。
阅读原文arxiv.org