Overcoming Challenges of Interpretive Structural Modeling with Large Language Models

利用大语言模型克服解释结构模型（ISM）的挑战

Abstract: Interpretive Structural Modeling (ISM) is a well-known process for multi-criteria decision making. The success of ISM over other methodologies is its ability to model causal relationships, the binary scale of factors, and resulting hierarchical representation.

摘要： 解释结构模型（Interpretive Structural Modeling, ISM）是一种众所周知的多准则决策过程。ISM 相比其他方法论的成功之处在于其能够对因果关系、因素的二元尺度以及由此产生的层次结构进行建模。

Traditionally, the modeling process is performed by repeated interactions with subject matter experts until consensus is reached. This process is tedious, labor-intense, and most importantly limits the ability of ISM to scale to studies with hundreds of variables.

传统上，建模过程是通过与领域专家反复互动直至达成共识来完成的。这一过程既繁琐又耗费人力，最重要的是，它限制了 ISM 在处理包含数百个变量的研究时的扩展能力。

Drawing on existing work of causal graph discovery with large language models (LLM) as imperfect experts, this work explores an integrated LLM-ISM approach for ISM. Pairwise, k-wise, rowwise, and full graph discovery methodologies are compared and evaluated.

借鉴现有利用大语言模型（LLM）作为“不完美专家”进行因果图发现的研究，本文探索了一种用于 ISM 的集成 LLM-ISM 方法。文中对成对（Pairwise）、k-元（k-wise）、行式（rowwise）和全图（full graph）发现方法进行了比较和评估。

It is shown that causal graph discovery methods for ISM perform best using rowwise (SHD=160, F1-score=0.77) and full graph methods (SHD=135, F1-score=0.73).

研究表明，用于 ISM 的因果图发现方法在采用行式（SHD=160，F1-score=0.77）和全图方法（SHD=135，F1-score=0.73）时表现最佳。