发表机构
Oak Ridge National Laboratory; University of Tennessee（橡树岭国家实验室; 田纳西大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出利用大型语言模型作为不完美专家，集成LLM-ISM方法以自动化解释结构建模，通过比较多种因果图发现方法，发现逐行和全图方法表现最优，有效克服传统ISM的扩展性挑战。
AI 中文摘要
解释结构建模（ISM）是一种著名的多准则决策过程。ISM相对于其他方法论的成功之处在于其能够对因果关系、因素的二元规模以及由此产生的层次结构进行建模。传统上，建模过程通过与领域专家反复互动直到达成共识来进行。这一过程繁琐、劳动密集，最重要的是限制了ISM扩展到包含数百个变量的研究的能力。借鉴现有利用大型语言模型（LLM）作为不完美专家进行因果图发现的工作，本研究探索了一种用于ISM的集成LLM-ISM方法。比较并评估了成对、k-wise、逐行和全图发现方法。结果表明，用于ISM的因果图发现方法在逐行（SHD=160，F1分数=0.77）和全图方法（SHD=135，F1分数=0.73）上表现最佳。
英文摘要
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. 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. 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. 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).
CommentsThis preprint has not undergone peer review or any post-submission improvements or corrections
