
Doctoral Researcher
Joe Yu
Design science for GenAI systems, LLM data quality & LLM agents for retrieval and extraction
Joe is a PhD candidate in the BMW doctoral program and a Research Associate at the Chair for Strategy and Organization at TUM. His research focuses on designing, building and evaluating Generative AI systems, including solutions based on open-source models, for business applications ranging from enterprise question answering and information extraction to regulatory change detection. He is particularly interested in data quality, system reliability and the performance of LLM agents in retrieval and extraction settings.
Research topics
- Design Science Research for GenAI Applications
- Data Quality & Reliability of LLM Outputs
- LLM Agents for Retrieval and Information Extraction
- AI for Regulatory Change Detection & Compliance
Conference Contributions
Conference Papers
- Yu, J., & Welpe, I. M. (in press). Designing source-grounded GenAI systems for trustworthy technology scouting in cost engineering. In Proceedings of the 60th Hawaii International Conference on System Sciences (HICSS-60).
- Yu, J., Li, K. C., Treffers, T., & Welpe, I. M. (in press). From detection to decision: A human-centered artifact for regulatory change review. In Proceedings of the 47th International Conference on Information Systems (ICIS 2026).
- Yu, J., Li, K. C., & Ostarek, J. (2026). RegTrack: A fine-grained benchmark for multi-class legal change detection. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026): Student Research Workshop (pp. 764–778). https://doi.org/10.18653/v1/2026.acl-srw.68
- Yu, J., & Zhang, Y. (2026). Designing an LLM agent for enterprise question answering over heterogeneous documents. In Proceedings of the Pacific Asia Conference on Information Systems (PACIS 2026) (Paper 10). https://aisel.aisnet.org/pacis2026/practioner/practioner/10
- Yu, J., Born, N., & Treffers, T. (2026). From news to data: A hybrid LLM pipeline for robust person-centric information extraction. In Proceedings of the Pacific Asia Conference on Information Systems (PACIS 2026) (Paper 21). https://aisel.aisnet.org/pacis2026/ai_ml/ai_ml/21
Academic Service
- Co-organizer, Post-ECIS Research Exchange on Information Systems, Strategy, Organization, and AI. Technical University of Munich (TUM), June 2026.