---
_id: '14001'
abstract:
- lang: eng
  text: In recent years, Retrieval Augmented Generation (RAG) has emerged as a promising
    technology for designing application-specific chatbots. RAG combines a Large Language
    Model (LLM) with application-specific information provided via a database. This
    opens up the possibility for companies to at least partially automate existing
    business processes using RAG. One use case relates to work preparation at a mechanical
    engineering company. Due to the high complexity of the products and the wide variety
    of variants, creating assembly instructions for individual assemblies and modules
    involves a considerable amount of administrative work. The use of RAG can help
    to significantly improve the efficiency of this process. However, a key challenge
    is to ensure high quality of automatically generated assembly instructions. While
    existing research has focused on feedback mechanisms for improving LLMs, the effectiveness
    of different prompt-based feedback types on RAG-generated technical documentation
    quality has not yet been sufficiently investigated. This article therefore explores
    how quality of assembly instructions can be improved by integrating feedback mechanisms
    into a RAG system. For this purpose, two different feedback mechanisms were used
    in a laboratory experiment. On the one hand, an exclusively quantitative feedback
    mechanism was used. On the other hand, quantitative and qualitative feedback were
    combined. The results demonstrate that feedback mechanisms contribute to improving
    quality of information in assembly instructions. In addition, it was found that
    exclusively quantitative feedback leads to similarly good results as more complex
    combined feedback.
author:
- first_name: Julia
  full_name: Becker, Julia
  last_name: Becker
- first_name: Benjamin
  full_name: Adrian, Benjamin
  id: '42266'
  last_name: Adrian
- first_name: Dominik
  full_name: Green, Dominik
  id: '85489'
  last_name: Green
- first_name: Sven
  full_name: Hinrichsen, Sven
  id: '49010'
  last_name: Hinrichsen
citation:
  ama: Becker J, Adrian B, Green D, Hinrichsen S. Evaluating feedback mechanisms in
    the automatic creation of assembly instructions using retrieval-augmented generation.
    <i>Procedia CIRP</i>. 2026;146:243-248. doi:<a href="https://doi.org/10.1016/j.procir.2026.03.242">10.1016/j.procir.2026.03.242</a>
  apa: Becker, J., Adrian, B., Green, D., &#38; Hinrichsen, S. (2026). Evaluating
    feedback mechanisms in the automatic creation of assembly instructions using retrieval-augmented
    generation. <i>Procedia CIRP</i>, <i>146</i>, 243–248. <a href="https://doi.org/10.1016/j.procir.2026.03.242">https://doi.org/10.1016/j.procir.2026.03.242</a>
  bjps: <b>Becker J <i>et al.</i></b> (2026) Evaluating Feedback Mechanisms in the
    Automatic Creation of Assembly Instructions Using Retrieval-Augmented Generation.
    <i>Procedia CIRP</i> <b>146</b>, 243–248.
  chicago: 'Becker, Julia, Benjamin Adrian, Dominik Green, and Sven Hinrichsen. “Evaluating
    Feedback Mechanisms in the Automatic Creation of Assembly Instructions Using Retrieval-Augmented
    Generation.” <i>Procedia CIRP</i> 146 (2026): 243–48. <a href="https://doi.org/10.1016/j.procir.2026.03.242">https://doi.org/10.1016/j.procir.2026.03.242</a>.'
  chicago-de: 'Becker, Julia, Benjamin Adrian, Dominik Green und Sven Hinrichsen.
    2026. Evaluating feedback mechanisms in the automatic creation of assembly instructions
    using retrieval-augmented generation. <i>Procedia CIRP</i> 146: 243–248. doi:<a
    href="https://doi.org/10.1016/j.procir.2026.03.242">10.1016/j.procir.2026.03.242</a>,
    .'
  din1505-2-1: '<span style="font-variant:small-caps;">Becker, Julia</span> ; <span
    style="font-variant:small-caps;">Adrian, Benjamin</span> ; <span style="font-variant:small-caps;">Green,
    Dominik</span> ; <span style="font-variant:small-caps;">Hinrichsen, Sven</span>:
    Evaluating feedback mechanisms in the automatic creation of assembly instructions
    using retrieval-augmented generation. In: <i>Procedia CIRP</i> Bd. 146, Elsevier
    BV (2026), S. 243–248'
  havard: J. Becker, B. Adrian, D. Green, S. Hinrichsen, Evaluating feedback mechanisms
    in the automatic creation of assembly instructions using retrieval-augmented generation,
    Procedia CIRP. 146 (2026) 243–248.
  ieee: 'J. Becker, B. Adrian, D. Green, and S. Hinrichsen, “Evaluating feedback mechanisms
    in the automatic creation of assembly instructions using retrieval-augmented generation,”
    <i>Procedia CIRP</i>, vol. 146, pp. 243–248, 2026, doi: <a href="https://doi.org/10.1016/j.procir.2026.03.242">10.1016/j.procir.2026.03.242</a>.'
  mla: Becker, Julia, et al. “Evaluating Feedback Mechanisms in the Automatic Creation
    of Assembly Instructions Using Retrieval-Augmented Generation.” <i>Procedia CIRP</i>,
    vol. 146, 2026, pp. 243–48, <a href="https://doi.org/10.1016/j.procir.2026.03.242">https://doi.org/10.1016/j.procir.2026.03.242</a>.
  short: J. Becker, B. Adrian, D. Green, S. Hinrichsen, Procedia CIRP 146 (2026) 243–248.
  ufg: '<b>Becker, Julia u. a.</b>: Evaluating feedback mechanisms in the automatic
    creation of assembly instructions using retrieval-augmented generation, in: <i>Procedia
    CIRP</i> 146 (2026),  S. 243–248.'
  van: Becker J, Adrian B, Green D, Hinrichsen S. Evaluating feedback mechanisms in
    the automatic creation of assembly instructions using retrieval-augmented generation.
    Procedia CIRP. 2026;146:243–8.
date_created: 2026-09-04T15:04:12Z
date_updated: 2026-09-04T15:07:36Z
department:
- _id: DEP7020
- _id: DEP1305
doi: 10.1016/j.procir.2026.03.242
intvolume: '       146'
language:
- iso: eng
page: 243-248
publication: Procedia CIRP
publication_identifier:
  issn:
  - 2212-8271
publication_status: published
publisher: Elsevier BV
quality_controlled: '1'
status: public
title: Evaluating feedback mechanisms in the automatic creation of assembly instructions
  using retrieval-augmented generation
type: scientific_journal_article
user_id: '49010'
volume: 146
year: '2026'
...