Causal-Audit: Explicit and Auditable Graph-based Reasoning via Target-Aware Causal Chain Construction

Causal-Audit：通过目标感知因果链构建实现显式且可审计的图推理

Abstract: Causal and intervention-based question answering is fundamental to advancing large language models (LLMs) toward reasoning beyond surface-level correlations and understanding underlying causal mechanisms. However, existing LLM-based methods often rely on implicit language-level reasoning, resulting in opaque causal assumptions, unverifiable reasoning paths, and fragile predictions under complex interventions, particularly in context-free settings.

摘要： 基于因果和干预的问答系统对于推动大语言模型（LLM）超越表层相关性推理并理解潜在因果机制至关重要。然而，现有的基于 LLM 的方法往往依赖于隐式的语言级推理，导致因果假设不透明、推理路径不可验证，且在复杂干预下（特别是在无上下文设置中）预测结果较为脆弱。

In this paper, we propose an explicit and auditable causal reasoning framework for context-free intervention-based question answering. Our method formulates causal inference as structured reasoning over an explicit causal graph through four modular stages, rather than implicit end-to-end prediction.

在本文中，我们提出了一种用于无上下文干预问答的显式且可审计的因果推理框架。我们的方法将因果推理表述为通过四个模块化阶段在显式因果图上进行的结构化推理，而非隐式的端到端预测。

A key innovation is a target-aware causal graph construction strategy that treats the target variable as a core constraint during graph expansion, effectively suppressing irrelevant variables, spurious causal relations, and reasoning noise. We further introduce a path-level causal evidence aggregation mechanism that combines multiple causal paths while modeling both reinforcing and counteracting effects, enabling robust decision-making beyond single-chain reasoning.

一项关键创新是目标感知因果图构建策略，该策略在图扩展过程中将目标变量视为核心约束，从而有效抑制了无关变量、虚假因果关系和推理噪声。此外，我们引入了一种路径级因果证据聚合机制，该机制在结合多条因果路径的同时，对增强效应和抵消效应进行建模，从而实现了超越单链推理的稳健决策。

Extensive experiments on three benchmarks demonstrate that our framework consistently outperforms existing LLM-based methods while providing interpretable and auditable causal reasoning traces.

在三个基准测试上的大量实验表明，我们的框架始终优于现有的基于 LLM 的方法，同时提供了可解释且可审计的因果推理轨迹。