首页 > AI前沿 > Characterizing Predictive Multiplicity in Ranking and Its Fairness Implications

Characterizing Predictive Multiplicity in Ranking and Its Fairness Implications

arXiv机器学习 2026-11-12 00:45 17 阅读 查看原文
用户要求将一段纯文本新闻正文排版成语义化的HTML片段。 规则: 1. 只输出HTML片段本身,不要Markdown围栏、不要解释。 2. 每个自然段落用`

`包裹,长文用`

`/`

`划分小节。 3. 列表内容用`
  • `,引用用`
    `,代码用`
    `,重要句子可用``。
    4. 保留原文所有信息,不得增删改内容。
    5. 不要输出``/``/``等文档级标签。
    
    正文内容:
    Prediction problems often admit competing models that achieve comparable performance yet produce conflicting outputs, a phenomenon known as predictive multiplicity. While this challenge has been extensively studied in classification tasks, its implications remain largely unexplored in ranking frameworks, which are critical for high-stakes societal decisions such as the allocation of welfare resources and social assistance. This paper investigates the phenomenon of predictive multiplicity in score-based ranking problems. We introduce formal definitions to capture multiplicity in ranking settings, supported by foundational theoretical guarantees. Furthermore, we examine the dual relationship between predictive multiplicity and algorithmic fairness in ranking problems: we analyze how model multiplicity can act as a potential source of unfairness, while demonstrating how exploring this decision space provides a principled avenue for discovering less discriminatory rankings. Finally, we complement our theoretical contributions with insightful empirical evaluations on both synthetic and real-world datasets, validating our analytical findings and illustrating their practical implications. Taken together, this work highlights the real-world relevance of predictive multiplicity in ranking and sheds light on the potential of leveraging this effect to achieve fairer outcomes.
    
    分析正文结构:
    这是一整段学术摘要。可以将其分为几个部分,用`

    `或`

    `划分小节,或者直接作为一个或多个`

    `段落。 由于原文是一整段,没有明显的列表、引用、代码。为了符合“长文用`

    `/`

    `划分小节”以及“重要句子可用``”,我可以将原文拆分成几个逻辑段落,或者加几个小标题。但是规则4要求“不得增删改内容”,如果加小标题,算不算“增”内容? “不得增删改内容”通常指不改变原文的文字内容。如果添加小标题(如“研究背景”、“研究内容”等),属于增加了原文没有的文字,违反了规则4。因此,不能添加新的小标题文字。 那“长文用`

    `/`

    `划分小节”怎么理解?如果原文本身没有小标题,我就不能用`

    `/`

    `去添加新标题,或者我可以将原文的某些句子作为小节标题?不,那会改变结构。 最安全的做法是:把原文按照自然逻辑分成几个`

    `,或者如果必须用`

    /

    `,可以将原文中的某句作为标题?不,原文没有标题。 或者,我可以直接将整段作为几个`

    `,不强行加`

    /

    `,因为“长文用`

    /

    `划分小节”是条件性的,如果不是长文或者没有小节,就不需要。但为了体现排版能力,我可以在不增加文字的前提下,把原文拆分成几个`

    `。 等等,如果把原文拆分成多个`

    `,是否算“改内容”?只要文字一致,段落拆分是排版的一部分,不算改内容。 原文: "Prediction problems often admit competing models that achieve comparable performance yet produce conflicting outputs, a phenomenon known as predictive multiplicity. While this challenge has been extensively studied in classification tasks, its implications remain largely unexplored in ranking frameworks, which are critical for high-stakes societal decisions such as the allocation of welfare resources and social assistance. This paper investigates the phenomenon of predictive multiplicity in score-based ranking problems. We introduce formal definitions to capture multiplicity in ranking settings, supported by foundational theoretical guarantees. Furthermore, we examine the dual relationship between predictive multiplicity and algorithmic fairness in ranking problems: we analyze how model multiplicity can act as a potential source of unfairness, while demonstrating how exploring this decision space provides a principled avenue for discovering less discriminatory rankings. Finally, we complement our theoretical contributions with insightful empirical evaluations on both synthetic and real-world datasets, validating our analytical findings and illustrating their practical implications. Taken together, this work highlights the real-world relevance of predictive multiplicity in ranking and sheds light on the potential of leveraging this effect to achieve fairer outcomes." 可以拆分为3个`

    `:

    Prediction problems often admit competing models that achieve comparable performance yet produce conflicting outputs, a phenomenon known as predictive multiplicity. While this challenge has been extensively studied in classification tasks, its implications remain largely unexplored in ranking frameworks, which are critical for high-stakes societal decisions such as the allocation of welfare resources and social assistance.

    This paper investigates the phenomenon of predictive multiplicity in score-based ranking problems. We introduce formal definitions to capture multiplicity in ranking settings, supported by foundational theoretical guarantees. Furthermore, we examine the dual relationship between predictive multiplicity and algorithmic fairness in ranking problems: we analyze how model multiplicity can act as a potential source of unfairness, while demonstrating how exploring this decision space provides a principled avenue for discovering less discriminatory rankings.

    Finally, we complement our theoretical contributions with insightful empirical evaluations on both synthetic and real-world datasets, validating our analytical findings and illustrating their practical implications. Taken together, this work highlights the real-world relevance of predictive multiplicity in ranking and sheds light on the potential of leveraging this effect to achieve fairer outcomes.

    这样没有增加任何文字,只是分段和加了几个``标签。 检查规则: 1. 只输出HTML片段本身,不要Markdown围栏、不要解释。 -> 好的。 2. 每个自然段落用`

    `包裹,长文用`

    `/`

    `划分小节。 -> 由于原文没有小节标题,强行加标题会违反“不得增删改内容”。所以用`

    `包裹自然段落即可。或者把第一句话作为`

    `?不,那改变了文本的语义层级,且属于删改。直接用`

    `最稳妥。 3. 列表内容用`

    • `,引用用`
      `,代码用`
      `,重要句子可用``。 -> 用``标出重要概念,如“predictive multiplicity”、“algorithmic fairness”。
      4. 保留原文所有信息,不得增删改内容。 -> 严格保留所有单词、标点(除了HTML标签)。注意,原文的标点要保留。
      5. 不要输出``/``/``等文档级标签。 -> 好的。
      
      再检查原文内容,确保一字不差:
      Prediction problems often admit competing models that achieve comparable performance yet produce conflicting outputs, a phenomenon known as predictive multiplicity. 
      While this challenge has been extensively studied in classification tasks, its implications remain largely unexplored in ranking frameworks, which are critical for high-stakes societal decisions such as the allocation of welfare resources and social assistance. 
      This paper investigates the phenomenon of predictive multiplicity in score-based ranking problems. 
      We introduce formal definitions to capture multiplicity in ranking settings, supported by foundational theoretical guarantees. 
      Furthermore, we examine the dual relationship between predictive multiplicity and algorithmic fairness in ranking problems: we analyze how model multiplicity can act as a potential source of unfairness, while demonstrating how exploring this decision space provides a principled avenue for discovering less discriminatory rankings. 
      Finally, we complement our theoretical contributions with insightful empirical evaluations on both synthetic and real-world datasets, validating our analytical findings and illustrating their practical implications. 
      Taken together, this work highlights the real-world relevance of predictive multiplicity in ranking and sheds light on the potential of leveraging this effect to achieve fairer outcomes.
      
      排版后:
      

      Prediction problems often admit competing models that achieve comparable performance yet produce conflicting outputs, a phenomenon known as predictive multiplicity. While this challenge has been extensively studied in classification tasks, its implications remain largely unexplored in ranking frameworks, which are critical for high-stakes societal decisions such as the allocation of welfare resources and social assistance.

      This paper investigates the phenomenon of predictive multiplicity in score-based ranking problems. We introduce formal definitions to capture multiplicity in ranking settings, supported by foundational theoretical