用模块化提示提升大模型因果发现能力，效果接近三倍提升
Causal Reasoning in Pieces: Modular In-Context Learning for Causal Discovery
- 设计分步提示框架，借鉴思维链思想拆解因果推理任务
- 在Corr2Cause数据集上性能接近基准的三倍，抗数据扰动能力强
- 适合需要可靠因果推断的研究者，尤其关注可解释性与泛化能力
因果推断仍是大语言模型面临的核心挑战。我们研究了在Corr2Cause基准上使用OpenAI o系列和DeepSeek-R模型家族进行因果发现的表现，发现这些以推理为核心的架构相比以往方法实现了显著的原生提升。为此，我们提出一种受思维树和思维链启发的模块化上下文学习流程，使性能近乎提升三倍。通过分析推理链长度、复杂度，并对传统模型与推理模型进行定性和定量对比，我们发现尽管先进推理模型已实现重大进步，但精心设计的上下文框架仍是充分发挥其潜力的关键。该方法为跨领域因果发现提供了可复现的通用范式。
原文摘要 · Abstract (English)
Causal inference remains a fundamental challenge for large language models. Recent advances in internal reasoning with large language models have sparked interest in whether state-of-the-art reasoning models can robustly perform causal discovery-a task where conventional models often suffer from severe overfitting and near-random performance under data perturbations. We study causal discovery on the Corr2Cause benchmark using the emergent OpenAI's o-series and DeepSeek-R model families and find that these reasoning-first architectures achieve significantly greater native gains than prior approaches. To capitalize on these strengths, we introduce a modular in-context pipeline inspired by the Tree-of-Thoughts and Chain-of-Thoughts methodologies, yielding nearly three-fold improvements over conventional baselines. We further probe the pipeline's impact by analyzing reasoning chain length, complexity, and conducting qualitative and quantitative comparisons between conventional and reasoning models. Our findings suggest that while advanced reasoning models represent a substantial leap forward, carefully structured in-context frameworks are essential to maximize their capabilities and offer a generalizable blueprint for causal discovery across diverse domains.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。