arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2409.11564cs.CLcs.AIcs.CVcs.LGeess.AS
收藏

面向语言、语音与视觉任务的基于人类反馈的偏好调优:一项综述

Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey

Capital One(第一资本金融公司);Columbia University(哥伦比亚大学)

Genta Indra Winata, Hanyang Zhao, Anirban Das, Wenpin Tang, David D. Yao, Shi-Xiong Zhang, Sambit Sahu

AI总结:

该综述系统梳理多模态偏好调优及人类反馈整合的最新进展,从基础理论、方法分类、应用与未来方向三方面展开,旨在为相关研究者和从业者提供领域全景,推动后续创新。

摘要:

偏好调优是使深度生成模型与人类偏好对齐的关键过程。本综述全面梳理了偏好调优及人类反馈整合领域的最新进展。论文分为三大核心部分:1)引言与基础:介绍强化学习框架、偏好调优任务,以及语言、语音、视觉等多模态下的模型与数据集,还有不同的策略方法;2)各类偏好调优方法的深度探究:对偏好调优中使用的方法进行详细分析;3)应用、讨论与未来方向:探索偏好调优在下游任务中的应用,包括不同模态的评估方法,并对未来研究方向作出展望。我们的目标是呈现偏好调优与模型对齐领域的最新方法论,提升研究者和从业者对该领域的理解,同时希望推动该领域更多的参与和创新。

英文摘要:

Preference tuning is a crucial process for aligning deep generative models with human preferences. This survey offers a thorough overview of recent advancements in preference tuning and the integration of human feedback. The paper is organized into three main sections: 1) introduction and preliminaries: an introduction to reinforcement learning frameworks, preference tuning tasks, models, and datasets across various modalities: language, speech, and vision, as well as different policy approaches, 2) in-depth exploration of each preference tuning approach: a detailed analysis of the methods used in preference tuning, and 3) applications, discussion, and future directions: an exploration of the applications of preference tuning in downstream tasks, including evaluation methods for different modalities, and an outlook on future research directions. Our objective is to present the latest methodologies in preference tuning and model alignment, enhancing the understanding of this field for researchers and practitioners. We hope to encourage further engagement and innovation in this area.

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。

↑