发表机构
School of Information and Communication Technology, Griffith University（信息与通信技术学院，格里菲斯大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对无上下文干预问答，提出因果审计框架，通过目标感知因果图构建和路径级因果证据聚合机制，将因果推理结构化，实验证明该框架优于现有方法，能提供可解释且可审计的推理痕迹。
AI 中文摘要
基于因果和干预的问答对于推动大语言模型超越表面相关性并理解潜在因果机制至关重要。现有基于大语言模型的方法常依赖隐式语言层面推理，导致因果假设不透明、推理路径不可验证以及复杂干预下预测脆弱。本文提出用于基于无上下文干预问答的显式且可审计的因果推理框架。该方法通过四个模块阶段将因果推理表述为在显式因果图上的结构化推理。关键创新是目标感知因果图构建策略，在图扩展时将目标变量视为核心约束，抑制无关变量等。还引入路径级因果证据聚合机制，结合多条因果路径并建模增强和抵消效应，实现超越单链推理的稳健决策。在三个基准上的大量实验表明，该框架始终优于现有基于大语言模型的方法，同时提供可解释且可审计的因果推理痕迹。
英文摘要
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. 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. 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. Extensive experiments on three benchmarks demonstrate that our framework consistently outperforms existing LLM-based methods while providing interpretable and auditable causal reasoning traces.
Journal refThe 64th Annual Meeting of the Association for Computational Linguistics 2026
