基于大语言模型的自然语言反事实因果推断
Counterfactual Causal Inference in Natural Language with Large Language Models
AI总结：
本研究针对非结构化自然语言因果推断难题，提出基于大语言模型的端到端方法，通过提取因果变量、构建并融合多源因果图开展反事实推断，可降低模型偏差，同时揭示了LLM反事实推理局限的成因并给出缓解方向。
摘要：
因果结构发现方法通常应用于结构化数据，这类数据中因果变量已知，且可通过统计检验评估因果关系。相比之下，由于缺乏已知变量或反事实数据来估计因果关联，从新闻文章等非结构化自然语言数据中还原因果结构面临诸多挑战。大语言模型（Large Language Models, LLMs）已在该方向展现出可观成效，但也存在局限性。本研究探究了LLM从文本文档构建因果图并执行反事实因果推断的能力。我们提出了一种从自然语言中实现因果结构发现与因果推断的端到端方法：首先利用LLM从文本数据中提取实例化的因果变量并构建因果图，再融合来自多数据源的因果图，以呈现尽可能全面的因果集合，随后在估计得到的图上开展反事实推断。因果图的条件约束能够减少LLM的偏差，更准确地表示因果估计量。我们通过该方法证实，LLM在反事实因果推理中的局限性源于预测误差，并提出了缓解这些问题的方向。我们还在真实世界的新闻文章上验证了该方法的适用性。
英文摘要：
Causal structure discovery methods are commonly applied to structured data where the causal variables are known and where statistical testing can be used to assess the causal relationships. By contrast, recovering a causal structure from unstructured natural language data such as news articles contains numerous challenges due to the absence of known variables or counterfactual data to estimate the causal links. Large Language Models (LLMs) have shown promising results in this direction but also exhibit limitations. This work investigates LLM's abilities to build causal graphs from text documents and perform counterfactual causal inference. We propose an end-to-end causal structure discovery and causal inference method from natural language: we first use an LLM to extract the instantiated causal variables from text data and build a causal graph. We merge causal graphs from multiple data sources to represent the most exhaustive set of causes possible. We then conduct counterfactual inference on the estimated graph. The causal graph conditioning allows reduction of LLM biases and better represents the causal estimands. We use our method to show that the limitations of LLMs in counterfactual causal reasoning come from prediction errors and propose directions to mitigate them. We demonstrate the applicability of our method on real-world news articles.
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。
