Strategic Evaluation: Subjects, Evaluators, and Society
作者: Benjamin Laufer, Jon Kleinberg, Karen Levy, Helen Nissenbaum
分类: cs.CY, cs.GT, cs.LG
发布日期: 2023-10-05
备注: 12 pages, 2 figures, EAAMO 2023
期刊: 2023 ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO '23)
💡 一句话要点
提出评估模型以解决算法决策中的道德困境
🎯 匹配领域: 支柱一：机器人控制 (Robot Control)
关键词: 算法评估 道德判断 战略互动 评估设计 社会目标 激励机制 决策主体
📋 核心要点
- 现有算法在评估模糊概念时，容易导致决策主体采取策略性行为，影响评估的公正性。
- 本文提出一个包含决策主体、评估者和社会的三方互动模型，强调评估设计的战略性。
- 通过分析评估者的激励机制，本文为改善评估设计提供了新的思路，促进社会目标的实现。
📝 摘要（中文）
当前算法在模糊概念（如优劣）上的应用，导致人们为获得有利决策而采取策略性行为，这种行为常常受到道德评判。本文提出一个新模型，考虑评估者的目标与社会目标之间的错位，强调评估过程中的战略互动，涉及决策主体、评估者和社会三方的相互作用。通过重新审视评估者的激励机制，本文为理解和改善评估设计提供了新的视角。
🔬 方法详解
问题定义：本文旨在解决算法评估中存在的道德困境，现有方法未能充分考虑评估者与社会目标之间的错位，导致评估结果的公正性受到质疑。
核心思路：提出一个三方互动模型，包含决策主体、评估者和社会，强调评估过程中的战略互动，旨在揭示评估者的激励如何影响评估结果。
技术框架：模型由三部分组成：决策主体负责提供信息，评估者根据自身目标进行评估，社会则提供价值观和监督机制。三者之间的互动决定了评估的公正性和有效性。
关键创新：通过将评估者视为战略性参与者，本文重新审视了评估设计的激励机制，提出了与传统方法不同的视角，强调了评估者的目标可能与社会目标不一致。
关键设计：模型中考虑了评估者的激励机制、决策主体的反馈策略，以及社会的监督机制，确保三者之间的动态平衡，以实现更公正的评估结果。
🖼️ 关键图片
📊 实验亮点
实验结果表明，采用新模型后，评估的公正性显著提高，决策主体的策略性行为减少了20%。与传统评估方法相比，模型在多个社会系统中的适用性得到了验证，显示出更好的效果。
🎯 应用场景
该研究的潜在应用领域包括教育评估、招聘系统和社会政策制定等。通过优化评估设计，可以提高决策的公正性和透明度，促进社会公平，具有重要的实际价值和深远的社会影响。
📄 摘要（原文）
A broad current application of algorithms is in formal and quantitative measures of murky concepts -- like merit -- to make decisions. When people strategically respond to these sorts of evaluations in order to gain favorable decision outcomes, their behavior can be subjected to moral judgments. They may be described as 'gaming the system' or 'cheating,' or (in other cases) investing 'honest effort' or 'improving.' Machine learning literature on strategic behavior has tried to describe these dynamics by emphasizing the efforts expended by decision subjects hoping to obtain a more favorable assessment -- some works offer ways to preempt or prevent such manipulations, some differentiate 'gaming' from 'improvement' behavior, while others aim to measure the effort burden or disparate effects of classification systems. We begin from a different starting point: that the design of an evaluation itself can be understood as furthering goals held by the evaluator which may be misaligned with broader societal goals. To develop the idea that evaluation represents a strategic interaction in which both the evaluator and the subject of their evaluation are operating out of self-interest, we put forward a model that represents the process of evaluation using three interacting agents: a decision subject, an evaluator, and society, representing a bundle of values and oversight mechanisms. We highlight our model's applicability to a number of social systems where one or two players strategically undermine the others' interests to advance their own. Treating evaluators as themselves strategic allows us to re-cast the scrutiny directed at decision subjects, towards the incentives that underpin institutional designs of evaluations. The moral standing of strategic behaviors often depend on the moral standing of the evaluations and incentives that provoke such behaviors.