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 2402.09236cs.LGcs.AImath.STstat.MLstat.TH
收藏

学习可解释概念:统一因果表示学习与基础模型

Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Models

Carnegie Mellon University(卡内基梅隆大学);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);Tübingen AI Center(蒂宾根人工智能中心);University of Chicago(芝加哥大学);ELLIS Institute Tübingen(ELLIS蒂宾根研究所)

Goutham Rajendran, Simon Buchholz, Bryon Aragam, Bernhard Schölkopf, Pradeep Ravikumar

AI总结:

本研究关联因果表示学习与基础模型两类智能系统构建路径,融合两领域思路定义可解释概念并证明其可从多样数据恢复,通过合成数据与大语言模型实验验证了统一方法的效用。

摘要:

构建智能机器学习系统主要有两类路径。一类是构建本质上可解释的模型,这正是不断发展的因果表示学习领域致力的方向。另一类是构建高性能的基础模型,随后投入研究力量去理解其工作机制。在本研究中,我们关联了这两类路径,探究如何从数据中学习人类可解释的概念。我们融合两个领域的思路,正式定义了概念的一种定义,并证明它们可从多样化数据中被恢复。在合成数据和大语言模型上开展的实验验证了我们统一方法的实用性。

英文摘要:

To build intelligent machine learning systems, there are two broad approaches. One approach is to build inherently interpretable models, as endeavored by the growing field of causal representation learning. The other approach is to build highly-performant foundation models and then invest efforts into understanding how they work. In this work, we relate these two approaches and study how to learn human-interpretable concepts from data. Weaving together ideas from both fields, we formally define a notion of concepts and show that they can be provably recovered from diverse data. Experiments on synthetic data and large language models show the utility of our unified approach.

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。

↑