Scholarlink

<p>Counterfactual explanations are widely used to communicate how inputs must change for a model to alter its prediction. For a single instance, many valid counterfactuals can exist, which leaves open the possibility for an explanation provider to cherry-pick explanations that better suit a narrative of their choice, highlighting favourable behaviour and withholding examples that reveal problematic behaviour. We formally <i>define</i> cherry-picking for counterfactual explanations. We then study to what extent an external auditor can <i>detect</i> such manipulation. Even with full procedural access, cherry-picked explanations can remain difficult to distinguish from non-cherry-picked explanations, because the multiplicity of valid counterfactuals and flexibility in the explanation specification provide sufficient degrees of freedom to mask deliberate selection. We demonstrate empirically that this variability often exceeds the effect of cherry-picking on standard counterfactual quality metrics. We therefore argue that safeguards should prioritise <i>ex ante standardisation</i> over the use of metrics ex post. Without these safeguards, explanations can become a tool for obfuscation rather than transparency.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

On the definition and detection of cherry-picking in counterfactual explanations

  • 期刊论文

  • 发表日期：

    2026年7月1日

查看全文
  • James Hinns,
  • Sofie Goethals,
  • Stephan Van der Veeken,
  • Theodoros Evgeniou,
  • David Martens

摘要

Counterfactual explanations are widely used to communicate how inputs must change for a model to alter its prediction. For a single instance, many valid counterfactuals can exist, which leaves open the possibility for an explanation provider to cherry-pick explanations that better suit a narrative of their choice, highlighting favourable behaviour and withholding examples that reveal problematic behaviour. We formally define cherry-picking for counterfactual explanations. We then study to what extent an external auditor can detect such manipulation. Even with full procedural access, cherry-picked explanations can remain difficult to distinguish from non-cherry-picked explanations, because the multiplicity of valid counterfactuals and flexibility in the explanation specification provide sufficient degrees of freedom to mask deliberate selection. We demonstrate empirically that this variability often exceeds the effect of cherry-picking on standard counterfactual quality metrics. We therefore argue that safeguards should prioritise ex ante standardisation over the use of metrics ex post. Without these safeguards, explanations can become a tool for obfuscation rather than transparency.