Workshop Goals

The main goals of GenAI4PM 2027 are to:

• Strengthen the established GenAI4PM research community by identifying open problems, sharing negative or inconclusive results, and shaping a forward-looking research agenda for the next years.
• Establish shared benchmarks, evaluation criteria, and reproducibility practices for generative AI in process mining, with a focus on quantitative comparison against established methods.
• Advance trustworthy and verifiable GenAI-enabled process intelligence, addressing reliability, explainability, robustness, fairness, hallucination mitigation, and correctness of generated artifacts.
• Connect researchers, practitioners, and tool builders across process mining, BPM, NLP, foundation models, and enterprise systems around concrete use cases and practical challenges.

Scope & Indicative Topics

GenAI4PM 2027 invites original contributions on how generative AI and foundation models can support, extend, or critically examine process mining research and practice. Topics of interest include, but are not limited to:

• Evaluation methodologies, shared benchmarks, challenge datasets, and reproducible experimental protocols for GenAI in process mining.
• Large language models and foundation models for event log extraction, ingestion, annotation, enrichment, abstraction, and quality improvement.
• LLM-assisted data preparation tasks such as ETL automation, CSV/database ingestion, and schema understanding for process mining.
• Text-to-process and process-to-text generation, including imperative and declarative process representations and correctness evaluation.
• Generative AI for process discovery, conformance checking, compliance, recommendation, and root-cause analysis, with empirical comparison to established algorithms or validation on real-world event logs.
• Object-centric, declarative, and multi-perspective process mining with generative AI, including semantics-aware approaches.
• Non-language foundation models for process analytics, including time-series, graph, and multimodal foundation models.
• Multimodal process mining and semantic integration of textual, interaction, and event data.
• Conversational process analytics, LLM-based Q&A, copilots, autonomous agents, and human-in-the-loop systems for process intelligence, supported by empirical user evaluations.
• Synthetic event data and process model generation, shared benchmarks, and evaluation protocols for GenAI-based process analysis.
• Trustworthiness challenges such as hallucination detection, robustness analysis, bias and fairness assessment, explainability, privacy, governance, and output verification.
• Integration of GenAI with BPM suites, enterprise systems, robotic process automation, task mining, and digital-worker platforms, including knowledge grounding and domain adaptation.
• Experience reports, case studies, datasets, tools, and empirical studies from academia or industry.

Submission Instructions

Submissions must use the Springer LNCS/LNBIP format (see the Springer conference proceedings guidelines). Submissions must be in English and cannot exceed 12 pages (including tables, figures, the bibliography, and appendices).

Each paper should contain a short abstract, clarifying the relation of the paper with the main topics (preferably using the list of topics above), clearly stating the problem being addressed, the goal of the work, the results achieved, and the relation to other work.

Papers should be submitted electronically as a self-contained PDF file via the EasyChair submission system. When submitting your paper, please select the workshop track “GenAI4PM 2027.”

Submissions must be original contributions that have not been published or submitted to other conferences or journals in parallel with this workshop.

Publication

Springer will publish all workshop papers as a post-workshop proceedings volume in the Lecture Notes in Business Information Processing (LNBIP) series.

Important Dates

• Abstract Submission: November 11, 2026 (AoE)
• Paper Submission: November 18, 2026 (AoE)
• Paper Acceptance Notification: December 21, 2026 (AoE)
• Pre-workshop Camera-Ready Papers: January 21, 2027 (AoE)
• Workshop: February 8, 2027
• Post-workshop Camera-Ready Papers: February 22, 2027

Registration

At least one author of each accepted paper must register and participate in person in the workshop. Please visit the ICPM 2027 conference website for registration information.

Organizers

Alessandro Berti

RWTH Aachen University, Germany

Alessandro Berti is a Software Engineer at RWTH Aachen University, affiliated with the Process and Data Science (PADS) group. His doctoral work focuses on object-centric process mining. He is a main developer of the pm4py Python library and has contributed to integrating large language models into process mining tooling and research.

Mohammadreza Fani Sani

Microsoft, Denmark

Mohammadreza Fani Sani is an Applied and Data Scientist at Microsoft, with a focus on large language model solutions for Copilot AI and process mining, including task orchestration through Microsoft Copilot Studio. He completed his doctorate in the PADS group at RWTH Aachen University, where he studied data preprocessing for improved process mining outcomes. His profile combines academic process mining expertise with hands-on industrial work on GenAI-enabled enterprise systems.

Humam Kourani

Fraunhofer Institute for Applied Information Technology (FIT), Germany

Humam Kourani is a Research Associate at Fraunhofer FIT and a member of the Center for Process Intelligence, contributing to research and software-development projects within the Data Science and Artificial Intelligence department. He also serves as a process mining examiner for the Fraunhofer Personnel Certification Authority and is pursuing his PhD at RWTH Aachen University. His work focuses on business process modeling, process discovery, and the integration of large language models into process mining.

Cristina Cabanillas

University of Seville, Spain

Cristina Cabanillas is a professor at the University of Seville working in business process management and process mining. Her research includes resource management, process optimization, and the use of generative AI, particularly large language models, to support process model discovery and analysis. Through her publications and collaborations, she has helped bridge cutting-edge AI technology and practical process improvement.

Program Committee

• Marco Comuzzi, Ulsan National Institute of Science and Technology (UNIST)
• Jan Mendling, WU Vienna University of Economics and Business
• Peter van der Putten, Leiden University / Pegasystems
• Vinicius Stein Dani, Utrecht University
• Amin Jalali, Stockholm University
• Janik Benzin, Technical University of Munich
• Thomas Hildebrandt, University of Copenhagen
• Flavia Santoro, Rio de Janeiro State University (UERJ)
• Manuel Resinas, University of Seville
• Massimiliano de Leoni, University of Padua
• David Chapela, University of Tartu
• Gabriel Marques Tavares, LMU Munich
• Mathias Weske, Hasso Plattner Institute, University of Potsdam
• Akhil Kumar, Penn State University
• Barbara Weber, University of St. Gallen
• Henrik Leopold, Kühne Logistics University
• Matthias Weidlich, Hasso Plattner Institute, University of Potsdam
• Anna Kalenkova, Adelaide University
• Lars Ackermann, Hof University of Applied Sciences
• Angelo Casciani, Sapienza University of Rome
• Alessandro Padella, University of Padua
• Mingjun Li, Tsinghua University
• Martin Käppel, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)
• Andrea Burattin, Technical University of Denmark
• Krzysztof Kluza, AGH University of Krakow
• Eduardo Illueca Fernández, Karolinska Institutet
• Iris Beerepoot, Utrecht University
• Gyunam Park, Eindhoven University of Technology / Fraunhofer FIT
• Majid Rafiei, SAP SE
• Mohsen Shirali, KU Leuven
• Simone Agostinelli, Universitas Mercatorum
• Ana Costa, Technical University of Munich
• Yorck Zisgen, University of Bayreuth
• Andrzej Janusz, Queensland University of Technology (QUT)
• Rob Bemthuis, University of Twente
• Chantale Lauer, DFKI / Saarland University
• Aaron Küsters, RWTH Aachen University
• Timotheus Kampik, Umeå University / SAP
• Anton Antonov, Celonis
• Fareed Zandkarimi, SAP Signavio
• Edyta Brzychczy, AGH University of Krakow
• Nataliia Klievtsova, Technical University of Munich
• Sandro Franzoi, University of Münster
• Chiara Di Francescomarino, University of Trento
• Faiza Bukhsh, University of Twente
• Marco Montali, Free University of Bozen-Bolzano
• Karolin Winter, Eindhoven University of Technology
• Irene Vanderfeesten, KU Leuven

Contact

For any questions about the workshop, please contact the organizers at genai4pm-2027@easychair.org.