生成模型增强推荐系统相关的算法危害
Algorithmic Harms Associated with Generative Model-Augmented Recommendation Systems
浏览论文内容
中文总结 AI 辅助
本研究扩展了算法危害分类法，分析生成模型增强推荐系统可能引发的新型及内生危害，并提供因果分析以支持检测与缓解。
中文摘要 AI 辅助
在本工作中，我们考虑了随着生成模型被整合到机器学习平台中可能出现的算法危害。我们认为现有的危害分类法和威胁模型需要扩展，以（1）解决研究充分的表征危害和服务质量危害的新颖因果驱动因素；（2）预测并缓解内生危害，例如净化，当系统输入与系统设计者的目标或生成模型的归纳先验不一致时，可能会出现这种危害。为此，我们引入了一个扩展的算法危害分类法，该分类法与在非对话式推荐系统中使用生成模型相关。此外，我们提供了关于（输入，输出）联合分布的问题子集如何产生的因果分析，以帮助危害检测和缓解工作。
英文摘要
In this work, we consider algorithmic harms that may arise as generative models are incorporated into machine learning platforms. We argue that existing harm taxonomies and threat models require extension to (1) address novel causal drivers of well-studied representational and quality-of-service harms; and (2) anticipate and mitigate endogenous harms, such as sanitization, which may arise when system inputs are misaligned with the system designer's objectives, or the generative model's inductive priors. To this end, we introduce an expanded taxonomy of algorithmic harms associated with the use of generative models in non-conversational recommendation systems. In addition, we offer a causal analysis of how problematic subsets of the (input, output) joint distribution can arise, in an effort to inform harms detection and mitigation efforts.
