相关还是因果：分析LLM与LRM推理过程的因果结构
Correlation or Causation: Analyzing the Causal Structures of LLM and LRM Reasoning Process
AI总结：
本文通过结构因果模型系统分析LLMs与LRMs的推理过程，发现RLVR训练能减少虚假相关、强化因果结构，从而提升推理忠实性并减少偏见。
摘要：
大语言模型（LLMs）存在严重的推理问题，如不忠实、偏见和不一致，因为它们缺乏稳健的因果基础，可能依赖表面相关性而非真正的理解。相继出现的LRMs作为一种有前景的替代方案，利用强化学习（RL）和蒸馏等先进训练技术来提高任务准确性。然而，这些训练方法对因果性的影响在很大程度上仍未得到探索。在本研究中，我们对LLMs和LRMs进行了系统的因果分析，考察了四个关键变量的结构因果模型（SCMs）：问题指令（Z）、思考过程（T）、推理步骤（X）和答案（Y）。我们的发现表明，经过RLVR训练的LRMs展现出增强的因果推理能力，更接近理想的因果结构，而LLMs和蒸馏LRMs未能解决与因果性相关的缺陷。我们进一步的研究表明，RLVR减少了虚假相关性并加强了真正的因果模式，从而减轻了不忠实和偏见。此外，我们对RLVR训练过程动态的检查观察到，减少的虚假特征与改进的因果结构之间存在高度相关性，其中因果关系在训练过程中持续改善。本研究有助于理解推理模型中的因果性，突出了RLVR在增强因果推理中的关键作用，并为设计具有更强因果基础的未来AI系统提供了见解。我们在https://github.com/Harryking1999/CoT_Causal_Analysis发布了代码和数据。
英文摘要：
LLMs suffer from critical reasoning issues such as unfaithfulness, bias, and inconsistency, since they lack robust causal underpinnings and may rely on superficial correlations rather than genuine understanding. Successive LRMs have emerged as a promising alternative, leveraging advanced training techniques such as reinforcement learning (RL) and distillation to improve task accuracy. However, the impact of these training methods on causality remains largely unexplored. In this study, we conduct a systematic causal analysis on LLMs and LRMs, examining structural causal models (SCMs) of four key variables: problem instruction (Z), thinking process (T), reasoning steps (X), and answer (Y). Our findings reveal that RLVR-trained LRMs exhibit enhanced causal reasoning capabilities, aligning more closely with ideal causal structures, while LLMs and distilled LRMs fail to address causality-related deficiencies. Our further investigation indicates that RLVR reduces spurious correlations and strengthens genuine causal patterns, thereby mitigating unfaithfulness and bias. In addition, our inspection on the dynamics of the RLVR training process observes a high correlation between reduced spurious features and improved causal structures, where the causal relationships consistently improve in the training process. This study contributes to the understanding of causality in reasoning models, highlights the critical role of RLVR in enhancing causal reasoning, and provides insights for designing future AI systems with stronger causal foundations. We release our code and data at https://github.com/Harryking1999/CoT_Causal_Analysis.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
