提出响应性验证方法，评估模型在输入变化时输出是否改变及改变频率。
Responsiveness Verification: Will Predictions Change? How Much? How Often?
- 通过输入扰动概率衡量模型响应性，量化输出变动可能性。
- 在再犯预测、内容审核等场景中发现模型易被操纵或失效的漏洞。
- 适用于需要安全验证的AI系统，如司法、内容审查和大模型评测。
机器学习模型常用于输入因常规交互、策略操纵或噪声而变化的场景，此类变化可能导致模型在未见过的输入区域做出预测，从而威胁安全性。本文提出通过测量‘响应性’来应对该问题——即在特定交互模型下，输入变化时模型输出发生变化的概率。我们开发了适用于任意机器学习模型的响应性估计算法，并构建了一个可定义广泛交互模型的框架。结合统计保证，支持实际验证。通过三个应用展示其价值：在再犯预测中检测到模型预判被排除的风险，在内容审核中估算博弈成本，在大模型基准测试中检验其鲁棒性。
原文摘要 · Abstract (English)
Machine learning models are often used in applications where their inputs change due to routine interactions, strategic manipulation, or noise. In such settings, models can undermine safety as these changes lead them to predict over regions of input space they have not seen. We propose to address these challenges by measuring responsiveness---the probability that a model output changes when its inputs change under an interaction model. We develop algorithms to estimate responsiveness for any machine learning model, and a framework to specify broad classes of interaction models. We pair these algorithms with statistical guarantees that support practical validation. We demonstrate how our tools can promote safety and reliability across domains by detecting preclusion in recidivism prediction, estimating the cost of gaming in content moderation, and testing the robustness of benchmarks for LLMs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。