arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.08145cs.LGcs.AIcs.CLcs.CVcs.CY
收藏

可靠且负责任的基础模型:全面综述

Reliable and Responsible Foundation Models: A Comprehensive Survey

Xinyu Yang, Junlin Han, Rishi Bommasani, Jinqi Luo, Wenjie Qu, Wangchunshu Zhou, Adel Bibi, Xiyao Wang, Jaehong Yoon, Elias Stengel-Eskin, Shengbang Tong, Lingf… 展开作者

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

AI总结:

本文综述了基础模型的可靠和负责任发展,探讨了偏见、安全、不确定性等关键问题,并提出了未来研究方向。

摘要:

基础模型,包括大型语言模型(LLMs)、多模态大型语言模型(MLLMs)、图像生成模型(即文本到图像模型和图像编辑模型)以及视频生成模型,已成为在法律、医学、教育、金融、科学等各个领域广泛应用的必不可少的工具。随着这些模型在现实世界中的应用日益增加,确保其可靠性和责任性对学术界、工业界和政府而言都变得至关重要。本文综述针对基础模型的可靠和负责任的发展。我们探讨了关键问题,包括偏见和公平性、安全性和隐私、不确定性、可解释性和分布偏移。我们的研究还涵盖了模型的限制,如幻觉,以及对齐和人工智能生成内容(AIGC)检测等方法。对于每个领域,我们回顾了该领域的现状,并概述了具体的未来研究方向。此外,我们讨论了这些领域的交叉点,突显了它们的联系和共同挑战。我们希望我们的综述能促进发展出不仅强大而且道德、可信、可靠且社会负责的基础模型。

英文摘要:

Foundation models, including Large Language Models (LLMs), Multimodal Large Language Models (MLLMs), Image Generative Models (i.e, Text-to-Image Models and Image-Editing Models), and Video Generative Models, have become essential tools with broad applications across various domains such as law, medicine, education, finance, science, and beyond. As these models see increasing real-world deployment, ensuring their reliability and responsibility has become critical for academia, industry, and government. This survey addresses the reliable and responsible development of foundation models. We explore critical issues, including bias and fairness, security and privacy, uncertainty, explainability, and distribution shift. Our research also covers model limitations, such as hallucinations, as well as methods like alignment and Artificial Intelligence-Generated Content (AIGC) detection. For each area, we review the current state of the field and outline concrete future research directions. Additionally, we discuss the intersections between these areas, highlighting their connections and shared challenges. We hope our survey fosters the development of foundation models that are not only powerful but also ethical, trustworthy, reliable, and socially responsible.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑