让大模型先构建知识图谱再推理，显著提升因果推断能力
Structured Thinking Matters: Improving LLMs Generalization in Causal Inference Tasks
- 引导模型先构建结构化知识图谱，再回答因果问题
- 在Corr2Cause数据集上F1得分从32.71提升至48.26，提升超47.5%
- 适合需要强逻辑推理与泛化能力的因果分析场景
尽管取得显著进展，大语言模型在区分因果关系与相关性方面仍不可靠。最新在Corr2Cause数据集基准上的结果显示，当前最先进模型如GPT-4（F1分数：29.08）仅略优于随机基线（随机均匀，F1分数：20.38），表明其泛化能力有限。为解决这一问题，我们提出一种新型结构化方法：不直接回答因果问题，而是引导模型通过构建结构化知识图谱，系统编码给定的相关前提，从而回答因果问题。该中间表示显著增强模型的因果推理能力。在Corr2Cause测试子集上使用Qwen3-32B模型进行实验，相比标准直接提示方法，F1分数从32.71提升至48.26（相对提升超过47.5%），同时精确率和召回率均有明显改善。结果验证了赋予模型结构化思考能力的有效性，并展示了其在多样因果推断任务中广阔的应用潜力。
原文摘要 · Abstract (English)
Despite remarkable advances in the field, LLMs remain unreliable in distinguishing causation from correlation. Recent results from the Corr2Cause dataset benchmark reveal that state-of-the-art LLMs -- such as GPT-4 (F1 score: 29.08) -- only marginally outperform random baselines (Random Uniform, F1 score: 20.38), indicating limited capacity of generalization. To tackle this limitation, we propose a novel structured approach: rather than directly answering causal queries, we provide the model with the capability to structure its thinking by guiding the model to build a structured knowledge graph, systematically encoding the provided correlational premises, to answer the causal queries. This intermediate representation significantly enhances the model's causal capabilities. Experiments on the test subset of the Corr2Cause dataset benchmark with Qwen3-32B model (reasoning model) show substantial gains over standard direct prompting methods, improving F1 scores from 32.71 to 48.26 (over 47.5% relative increase), along with notable improvements in precision and recall. These results underscore the effectiveness of providing the model with the capability to structure its thinking and highlight its promising potential for broader generalization across diverse causal inference tasks.
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。