While self-reflection can enhance language model reliability, its underlying mechanisms remain opaque, with existing analyses often yielding correlation-based insights that fail to generalize. To address this, we introduce \textbf{\texttt{ReBeCA}} (self-\textbf{\texttt{Re}}flection \textbf{\texttt{Be}}havior explained through \textbf{\texttt{C}}ausal \textbf{\texttt{A}}nalysis), a framework that unveils the interpretable behavioral hierarchy governing the self-reflection outcome. By modeling self-reflection trajectories as causal graphs, ReBeCA isolates genuine determinants of performance through a three-stage Invariant Causal Prediction (ICP) pipeline. We establish three critical findings: (1) \textbf{Behavioral hierarchy:} Semantic behaviors of the model influence final self-reflection results hierarchically: directly or indirectly; (2) \textbf{Causation matters:} Generalizability in self-reflection effects is limited to just a few semantic behaviors; (3) \textbf{More $\mathbf{\neq}$ better:} The confluence of seemingly positive semantic behaviors, even among direct causal factors, can impair the efficacy of self-reflection. ICP-based verification identifies sparse causal parents achieving up to $49.6\%$ structural likelihood gains, stable across tasks where correlation-based patterns fail. Intervention studies on novel datasets confirm these causal relationships hold out-of-distribution ($p = .013, η^2_\mathrm{p} = .071$). ReBeCA thus provides a rigorous methodology for disentangling genuine causal mechanisms from spurious associations in self-reflection dynamics.

翻译：尽管自反思能够提升语言模型的可靠性，但其内在机制仍不透明，现有分析多局限于相关性研究，难以推广。为此，我们提出\textbf{\texttt{ReBeCA}}（通过\textbf{\texttt{因果分析}}阐释的\textbf{\texttt{自反思行为}}）框架，该框架揭示了支配自反思结果的可解释行为层次结构。通过将自反思轨迹建模为因果图，ReBeCA采用三阶段不变因果预测（ICP）流程分离出影响性能的真实决定因素。我们确立了三个关键发现：（1）\textbf{行为层次性：}模型的语义行为以直接或间接方式分层影响最终自反思结果；（2）\textbf{因果主导性：}自反思效果的可推广性仅局限于少数语义行为；（3）\textbf{多非即优：}看似积极的语义行为（即便是直接因果因素）若同时出现，反而可能削弱自反思效能。基于ICP的验证表明，稀疏因果父节点可实现高达$49.6\%$的结构似然增益，且在相关性模式失效的任务中保持稳定。对新数据集的干预研究证实这些因果关系具有分布外泛化能力（$p = .013, η^2_\mathrm{p} = .071$）。因此，ReBeCA为解构自反思动态中真实因果机制与虚假关联提供了严谨的方法论。