Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings
神经概念验证器:通过概念编码扩展证明者-验证者博弈
机构 * Zuse Institute Berlin, Germany ; AI \& ML Lab, Computer Science Department, TU Darmstadt ; Hessian Center for AI (hessian.AI) ; Lab1141 ; German Research Center for AI (DFKI) ; Institute of Mathematics, Technische Universit\"at Berlin, Germany ; Max Planck Institute for Informatics, SIC
AI总结 提出神经概念验证器(NCV)框架,结合概念编码与证明者-验证者博弈,实现高维输入的可验证分类,优于传统方法并缓解捷径行为。
Comments 28 pages, 5 figures, 12 tables, revised references. An earlier version of this work was presented at the ICML 2025 Workshop on Actionable Interpretability