让大模型学会物理因果关系，提升零样本推理能力
Inducing Causal World Models in LLMs for Zero-Shot Physical Reasoning
- 引入因果物理模块和干预损失，训练模型理解因果关系
- 在零样本物理推理任务上超越现有模型，新数据集表现显著提升
- 适合需要可靠物理推理的AI系统研发者参考
大型语言模型虽具备强大语言能力，但缺乏对物理动态的直觉理解，限制了其在需因果推理的实际场景中的应用。本文提出因果世界模型诱导（CWMI）框架，通过引入专用因果物理模块（CPM）和新的因果干预损失训练目标，使模型从多模态数据中学习因果关系。该方法引导模型预测假设干预的结果，而非仅捕捉统计相关性，从而建立对物理定律的稳健内部表征。实验表明，CWMI在零样本物理推理任务上显著优于当前最优的LLMs，包括PIQA基准和新提出的PhysiCa-Bench数据集。结果证明，构建因果世界模型是实现更可靠、泛化更强AI系统的关键一步。
原文摘要 · Abstract (English)
Large Language Models (LLMs), despite their advanced linguistic capabilities, fundamentally lack an intuitive understanding of physical dynamics, which limits their effectiveness in real-world scenarios that require causal reasoning. In this paper, we introduce Causal World Model Induction (CWMI), a novel framework designed to embed an explicit model of causal physics within an LLM. Our approach incorporates a dedicated Causal Physics Module (CPM) and a new training objective called Causal Intervention Loss, encouraging the model to learn cause-and-effect relationships from multimodal data. By training the model to predict the outcomes of hypothetical interventions instead of merely capturing statistical correlations, CWMI develops a robust internal representation of physical laws. Experimental results show that CWMI significantly outperforms state-of-the-art LLMs on zero-shot physical reasoning tasks, including the PIQA benchmark and our newly proposed PhysiCa-Bench dataset. These findings demonstrate that inducing a causal world model is a critical step toward more reliable and generalizable AI systems.
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。