用大模型实现多视角多层级因果推理，提升污染与疾病溯源效果
IFAR: Multi-Perspective and Multi-Level Causal Discovery with LLMs
- 提出IFAR框架，结合逆向推理与逐关系正向验证
- 在主流大模型上F1得分提升约40%，召回与精确率平衡
- 无需微调即可超越专用推理模型，适用范围广
大语言模型（LLMs）的推理能力快速发展，但其溯因推理仍缺乏深入探索。现有方法难以有效处理因果关系的多视角、多层级特性。为此，我们构建了名为DeepAbduction的专用数据集，聚焦污染与疾病成因追溯，填补该领域数据空白。本文提出逆-正溯因推理（IFAR）框架，支持零样本下多视角、多层级的溯因推理，结合通用逆向推理与逐关系正向验证机制。实验表明，相较于其他方法，IFAR在主流大模型上实现了约40%的F1分数提升，同时保持召回率与精确率的良好平衡。此外，IFAR能显著提升非推理型大模型的表现，使其超过经专门推理训练的模型，并在后者上同样有效。代码将在论文被接受后公开。
原文摘要 · Abstract (English)
Large language models (LLMs) have developed rapidly, and their reasoning capabilities have become a hot research topic. However, there is still limited exploration of abductive reasoning. The multi-perspective and multi-level of causes is one of the core challenges of abductive reasoning, which cannot be solved well by existing methods. We construct a specialized dataset named DeepAbduction, which is designed for tracing the causes of pollution and disease, addressing the lack of datasets in this field. We propose Inverse-Forward Abductive Reasoning (IFAR) framework for LLMs multi-perspective and multi-level abductive reasoning. IFAR is zero-shot and combines generalized backward reasoning with relation-by-relation forward verification. Experimental results show that IFAR achieves an improvement of approximately 40% in the F1 score compared to other methods under mainstream LLMs, while maintaining a balance between recall and precision. Furthermore, IFAR enhances the performance of non-reasoning LLMs to surpass LLMs which have been trained for reasoning, and remains effective when applied to the latter. Code will be released after the acceptance of our work.
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。