发表机构
Concordia University; McGill University（康考迪亚大学; 麦吉尔大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文综述了大语言模型中的上下文因果性，提出包含语义、干预和反事实因果的分类体系，分析现有研究局限，并指出基准与真实需求的差距及未来方向。
AI 中文摘要
理解上下文因果性对于大语言模型（LLMs）至关重要，因为它使模型能够在特定情境中准确识别因果关系，并支持更可靠的决策。尽管其重要性显著，但关于大语言模型上下文因果性的系统性探索仍然缺乏。为填补这一空白，我们对该主题进行了全面综述。在本综述中，我们首先提出了一个上下文因果性的分类体系，包括语义因果性、干预因果性和反事实因果性，并通过其核心因果问题、所需模型能力、代表性任务以及因果分析中的实际用途来刻画每个类别。随后，我们分析了现有研究并讨论了其主要局限性。最后，我们审视了当前基准与真实世界需求之间的差距，并概述了未来研究的有前景方向。我们的目标是阐明大语言模型上下文因果性的研究格局，强调其重要性，并突出有前景的未来方向。
英文摘要
Understanding contextual causality is critical for large language models (LLMs), as it enables them to accurately identify causal relations in specific situations and support more reliable decision-making. Despite its significance, a systematic exploration of contextual causality with LLMs is still lacking. To fill this gap, we present a comprehensive survey on this topic. In this survey, we first propose a taxonomy of contextual causality, consisting of semantic, intervention, and counterfactual causality, and characterize each category by its core causal question, required model capabilities, representative tasks, and practical uses in causality analysis. We then analyze existing studies and discuss their key limitations. Finally, we examine the gaps between current benchmarks and real-world needs and outline promising directions for future research. Our goal is to clarify the research landscape of contextual causality with LLMs, emphasize its importance, and highlight promising future directions.
CommentsAccepted to the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026)
