7–11 Sept 2025
Teaching Hub 502
Europe/London timezone

Intelligent Retrieval Systems for Accelerator Physics: Matching Retrieval Approaches to Use Cases

MOPMO13
8 Sept 2025, 16:00
2h
Mountford Hall, Liverpool Guild of Students

Mountford Hall, Liverpool Guild of Students

University of Liverpool
Poster Presentation MC09: Overview and Commissioning MOPMO

Speaker

Rasmus Ischebeck (Paul Scherrer Institute)

Description

Accelerator facilities generate diverse documentation, from technical reports to structured wikis and semi-structured logbooks, which complicates efficient knowledge access. While Retrieval-Augmented Generation (RAG) offers a path toward intelligent operator assistants, no single method is universally optimal. We present three use cases from PSI: for technical documentation, naive dense retrieval with summarization provides fast and interpretable access; for the AcceleratorWiki, a graph-augmented approach improves reasoning over hierarchies and cross-references; and for ELOG, an agentic pipeline with specialized agents supports multimodal interpretation, temporal reasoning, and iterative refinement. Together, these case studies illustrate how matching retrieval paradigms to data types enables reliable, context-aware assistance in accelerator operations.

Funding Agency

This project has received funding from the European Union’s Horizon 2020 Research and Innovation programme under Grant Agreement No 101004730 (I.FAST)

I have read and accept the Conference Policies Yes

Authors

Linus Stuhlmann (Paul Scherrer Institute) Mariusz Sapinski (Paul Scherrer Institute) Qing Dai (Paul Scherrer Institute) Rasmus Ischebeck (Paul Scherrer Institute)

Presentation materials

There are no materials yet.