---
res:
  bibo_abstract:
  - <jats:p>As a possible solution to the demographic change and the resulting knowledge
    loss due to retirements in the Energy sector, this study aimed to develop a generic
    pipeline to implement and evaluate proof-of-concepts (PoCs) for LLM-based assistance
    systems in new domains. Our pipeline contains an LLM-based data generation strategy
    based on documents, a retrieval-augmented generation (RAG) architecture utilizing
    prompting techniques on existing German LLMs, and an LLM-based automatic evaluation
    strategy. We leverage our pipeline to evaluate five LLMs using data from a German
    DSO. We found that the Llama3 and the Mistral model are appropriately aligned
    for the task. We plan to pilot the RAG architecture in the DSO's infrastructure
    for future research and continuously research improvements using the generated
    human demonstrations.</jats:p>@eng
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Sascha Benjamin
      foaf_name: Kaltenpoth, Sascha Benjamin
      foaf_surname: Kaltenpoth
      foaf_workInfoHomepage: http://www.librecat.org/personId=50640
  - foaf_Person:
      foaf_givenName: Oliver
      foaf_name: Müller, Oliver
      foaf_surname: Müller
      foaf_workInfoHomepage: http://www.librecat.org/personId=72849
  bibo_doi: 10.1145/3717413.3717415
  bibo_issue: '4'
  bibo_volume: 4
  dct_date: 2025^xs_gYear
  dct_isPartOf:
  - http://id.crossref.org/issn/2770-5331
  dct_language: eng
  dct_publisher: Association for Computing Machinery (ACM)@
  dct_title: Don't Touch the Power Line - A Proof-of-Concept for Aligned LLM-Based
    Assistance Systems to Support the Maintenance in the Electricity Distribution
    System@
...