Retrieval Augmented Generation with LLMs for Explaining Business Process Models

被引:0
|
作者
Minor, Mirjam [1 ]
Kaucher, Eduard [1 ]
机构
[1] Goethe Univ Frankfurt, Dept Business Informat, Frankfurt, Germany
关键词
Process-oriented CBR; Large Language models; Retrieval-Augmented Generation;
D O I
10.1007/978-3-031-63646-2_12
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Large language models (LLMs) and retrieval augmented generation (RAG) are undergoing rapid development. Considering a case base as a memory in a RAG system provides novel opportunities for text generation. In this paper, we investigate the role Case-Based Reasoning (CBR) could play for supporting RAG systems in generating accessible explanations of business process models. We experiment with two different case bases in a RAG system. Case base a) is dedicated to support prompt chaining by reusing index knowledge on the cases with the aim to deal with large process models that do not fit into the context window size of a recent LLM. Second, case base b) contains model-text pairs to serve as in-context examples to enhance prompt templates. Approach b) aims to improve the quality of generated text explanations for process models of normal size. Our contribution opens a novel application area for process-oriented CBR. Further, our case-based RAG system provides a contemporary alternative to traditional Natural Language Processing pipelines. The experimental results contribute to gain some insights on an inherent capability threshold of GPT-4 at which the performance decreases much earlier than having reached the given context window size, on the number of retrieved cases a recent RAG system should use as in-context examples, and on suitable prompt templates.
引用
收藏
页码:175 / 190
页数:16
相关论文
共 50 条
  • [41] Multimodal Retrieval Augmented Generation Evaluation Benchmark
    Sun, Tienlan
    Somalwar, Anaiy
    Chan, Hinson
    2024 IEEE 99TH VEHICULAR TECHNOLOGY CONFERENCE, VTC2024-SPRING, 2024,
  • [42] Retrieval-augmented generation versus document-grounded generation: a key distinction in large language models
    Koga, Shunsuke
    Ono, Daisuke
    Obstfeld, Amrom
    JOURNAL OF PATHOLOGY CLINICAL RESEARCH, 2025, 11 (01):
  • [43] Benchmarking Retrieval Augmented Generation in Quantitative Finance
    Onan, Aytug
    Dursun, Ege Dogan
    INTELLIGENT AND FUZZY SYSTEMS, VOL 2, INFUS 2024, 2024, 1089 : 64 - 74
  • [44] Artificial Intelligence Text Processing Using Retrieval-Augmented Generation: Applications in Business and Education Fields
    Posedaru, Bogdan-Stefan
    Pantelimon, Florin-Valeriu
    Dulgheru, Mihai-Nicolae
    Georgescu, Tiberiu-Marian
    PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON BUSINESS EXCELLENCE, 2024, 18 (01): : 209 - 222
  • [45] Layered Query Retrieval: An Adaptive Framework for Retrieval-Augmented Generation in Complex Question Answering for Large Language Models
    Huang, Jie
    Wang, Mo
    Cui, Yunpeng
    Liu, Juan
    Chen, Li
    Wang, Ting
    Li, Huan
    Wu, Jinming
    APPLIED SCIENCES-BASEL, 2024, 14 (23):
  • [46] DRAK: Unlocking Molecular Insights with Domain-Specific Retrieval-Augmented Knowledge in LLMs
    Liu, Jinzhe
    Huang, Xiangsheng
    Chen, Zhuo
    Fang, Yin
    NATURAL LANGUAGE PROCESSING AND CHINESE COMPUTING, PT II, NLPCC 2024, 2025, 15360 : 255 - 267
  • [47] Storage and retrieval of business process simulation models based on IDEF3
    2005, Systems Engineering Society of China, Beijing, China (25):
  • [48] Efficient Retrieval of Similar Business Process Models Based on Structure (Short Paper)
    Jin, Tao
    Wang, Jianmin
    Wen, Lijie
    ON THE MOVE TO MEANINGFUL INTERNET SYSTEMS: OTM 2011, PT I, 2011, 7044 : 56 - +
  • [49] Adaptive Control of Retrieval-Augmented Generation for Large Language Models Through Reflective Tags
    Yao, Chengyuan
    Fujita, Satoshi
    ELECTRONICS, 2024, 13 (23):
  • [50] Retrieval Augmented Chest X-Ray Report Generation using OpenAI GPT models
    Ranjit, Mercy
    Ganapathy, Gopinath
    Manuel, Ranjit
    Ganu, Tanuja
    MACHINE LEARNING FOR HEALTHCARE CONFERENCE, VOL 219, 2023, 219