用逐步减少输入数据来测试大模型生成流程解释的质量。
Evaluating LLM-Based Process Explanations under Progressive Behavioral-Input Reduction
- 从日志前缀逐步减少输入，测试解释质量变化
- 适度缩减输入后解释质量基本保持不变
- 适合资源受限场景下的流程分析优化
大型语言模型（LLMs）被越来越多地用于从事件日志中发现的流程模型生成文本解释。从大规模行为抽象（如直接跟随图或佩特里网）生成解释可能计算开销较大。本文对在逐步减少行为输入条件下解释质量进行了探索性评估，即从固定日志的逐步缩小前缀中发现模型。我们的流程包括：(i) 在多个输入规模下发现模型；(ii) 使用一个LLM生成解释；(iii) 用第二个LLM评估解释的完整性、瓶颈识别和改进建议。在合成日志上，适度缩减输入后解释质量基本保持稳定，表明存在可行的成本-质量权衡。研究为资源受限环境下更高效的LLM辅助流程分析提供了路径。由于评分基于LLM（提供相对信号而非真实标签），且数据为合成数据，该研究具有探索性质。
原文摘要 · Abstract (English)
Large Language Models (LLMs) are increasingly used to generate textual explanations of process models discovered from event logs. Producing explanations from large behavioral abstractions (e.g., directly-follows graphs or Petri nets) can be computationally expensive. This paper reports an exploratory evaluation of explanation quality under progressive behavioral-input reduction, where models are discovered from progressively smaller prefixes of a fixed log. Our pipeline (i) discovers models at multiple input sizes, (ii) prompts an LLM to generate explanations, and (iii) uses a second LLM to assess completeness, bottleneck identification, and suggested improvements. On synthetic logs, explanation quality is largely preserved under moderate reduction, indicating a practical cost-quality trade-off. The study is exploratory, as the scores are LLM-based (comparative signals rather than ground truth) and the data are synthetic. The results suggest a path toward more computationally efficient, LLM-assisted process analysis in resource-constrained settings.
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。