---
_id: '13730'
abstract:
- lang: eng
  text: 'This paper introduces an LLM-mediated AI Advisor that contextualizes and
    synthesizes heterogeneous explainable AI (XAI) outputs to support fast and calibrated
    misinformation judgments in time-sensitive social media settings. We define LLM-mediated
    XAI as a process in which a large language model aggregates, prioritizes, and
    translates heterogeneous XAI outputs into a context-sensitive explanation tailored
    to the user’s decision situation. Semantic features, XAI modules and LLM-based
    summarization and synthesis enable the generation of explanations that are adapted
    in three ways: compressed for time-efficient decisions, translated into non-technical
    language, and progressively expandable for deeper inspection. Through a mixed-methods
    user study, including a quantitative study and a qualitative study, we analyze
    how users interpret, challenge and strategically rely on LLM-mediated explanations
    during real-world misinformation assessment tasks. The findings indicate that
    the approach reduces time-to-decision and supports critical inspection without
    inducing over-reliance. Progressive disclosure and different techniques to present
    information favored different user needs while conversational functionality was
    rarely used due to unclear benefits and fear of confusion.'
author:
- first_name: Valentin
  full_name: Grimm, Valentin
  id: '74000'
  last_name: Grimm
- first_name: Jessica
  full_name: Rubart, Jessica
  id: '45672'
  last_name: Rubart
  orcid: 0000-0003-0937-3551
- first_name: Eelco
  full_name: Herder, Eelco
  last_name: Herder
- first_name: Carsten
  full_name: Röcker, Carsten
  id: '61525'
  last_name: Röcker
citation:
  ama: 'Grimm V, Rubart J, Herder E, Röcker C. <i>LLM-Mediated XAI Explanations: An
    AI Advisor for Fast and Calibrated Judgments on Potential Misinformation</i>.
    (Balke WT, Plötzky F, Spaniol M, et al., eds.). ACM; 2026:110-116. doi:<a href="https://doi.org/10.1145/3795513.3810452">https://doi.org/10.1145/3795513.3810452</a>'
  apa: 'Grimm, V., Rubart, J., Herder, E., &#38; Röcker, C. (2026). LLM-Mediated XAI
    Explanations: An AI Advisor for Fast and Calibrated Judgments on Potential Misinformation.
    In W.-T. Balke, F. Plötzky, M. Spaniol, E. Herder, L. Manikonda, H. Liu, L.-D.
    Ibáñez, R. Rezapour, &#38; ACM Press (Eds.), <i>WebSci Companion ’26: Companion
    Publication of the 2026 18th ACM Web Science Conference</i> (pp. 110–116). ACM.
    <a href="https://doi.org/10.1145/3795513.3810452">https://doi.org/10.1145/3795513.3810452</a>'
  bjps: '<b>Grimm V <i>et al.</i></b> (2026) <i>LLM-Mediated XAI Explanations: An
    AI Advisor for Fast and Calibrated Judgments on Potential Misinformation</i>,
    Balke W-T et al. (eds). New York, USA: ACM.'
  chicago: 'Grimm, Valentin, Jessica Rubart, Eelco Herder, and Carsten Röcker. <i>LLM-Mediated
    XAI Explanations: An AI Advisor for Fast and Calibrated Judgments on Potential
    Misinformation</i>. Edited by Wolf-Tilo Balke, Florian Plötzky, Marc Spaniol,
    Eelco Herder, Lydia Manikonda, Haiming Liu, Luis-Daniel Ibáñez, Rezvaneh Rezapour,
    and ACM Press. <i>WebSci Companion ’26: Companion Publication of the 2026 18th
    ACM Web Science Conference</i>. New York, USA: ACM, 2026. <a href="https://doi.org/10.1145/3795513.3810452">https://doi.org/10.1145/3795513.3810452</a>.'
  chicago-de: 'Grimm, Valentin, Jessica Rubart, Eelco Herder und Carsten Röcker. 2026.
    <i>LLM-Mediated XAI Explanations: An AI Advisor for Fast and Calibrated Judgments
    on Potential Misinformation</i>. Hg. von Wolf-Tilo Balke, Florian Plötzky, Marc
    Spaniol, Eelco Herder, Lydia Manikonda, Haiming Liu, Luis-Daniel Ibáñez, Rezvaneh
    Rezapour, und ACM Press. <i>WebSci Companion ’26: Companion Publication of the
    2026 18th ACM Web Science Conference</i>. New York, USA: ACM. doi:<a href="https://doi.org/10.1145/3795513.3810452">https://doi.org/10.1145/3795513.3810452</a>,
    .'
  din1505-2-1: '<span style="font-variant:small-caps;">Grimm, Valentin</span> ; <span
    style="font-variant:small-caps;">Rubart, Jessica</span> ; <span style="font-variant:small-caps;">Herder,
    Eelco</span> ; <span style="font-variant:small-caps;">Röcker, Carsten</span> ;
    <span style="font-variant:small-caps;"><span style="font-variant:small-caps;">Balke,
    W.-T.</span> ; <span style="font-variant:small-caps;">Plötzky, F.</span> ; <span
    style="font-variant:small-caps;">Spaniol, M.</span> ; <span style="font-variant:small-caps;">Herder,
    E.</span> ; <span style="font-variant:small-caps;">Manikonda, L.</span> ; <span
    style="font-variant:small-caps;">Liu, H.</span> ; <span style="font-variant:small-caps;">Ibáñez,
    L.-D.</span> ; <span style="font-variant:small-caps;">Rezapour, R.</span> ; u. a.</span>
    (Hrsg.): <i>LLM-Mediated XAI Explanations: An AI Advisor for Fast and Calibrated
    Judgments on Potential Misinformation</i>. New York, USA : ACM, 2026'
  havard: 'V. Grimm, J. Rubart, E. Herder, C. Röcker, LLM-Mediated XAI Explanations:
    An AI Advisor for Fast and Calibrated Judgments on Potential Misinformation, ACM,
    New York, USA, 2026.'
  ieee: 'V. Grimm, J. Rubart, E. Herder, and C. Röcker, <i>LLM-Mediated XAI Explanations:
    An AI Advisor for Fast and Calibrated Judgments on Potential Misinformation</i>.
    New York, USA: ACM, 2026, pp. 110–116. doi: <a href="https://doi.org/10.1145/3795513.3810452">https://doi.org/10.1145/3795513.3810452</a>.'
  mla: 'Grimm, Valentin, et al. “LLM-Mediated XAI Explanations: An AI Advisor for
    Fast and Calibrated Judgments on Potential Misinformation.” <i>WebSci Companion
    ’26: Companion Publication of the 2026 18th ACM Web Science Conference</i>, edited
    by Wolf-Tilo Balke et al., ACM, 2026, pp. 110–16, <a href="https://doi.org/10.1145/3795513.3810452">https://doi.org/10.1145/3795513.3810452</a>.'
  short: 'V. Grimm, J. Rubart, E. Herder, C. Röcker, LLM-Mediated XAI Explanations:
    An AI Advisor for Fast and Calibrated Judgments on Potential Misinformation, ACM,
    New York, USA, 2026.'
  ufg: '<b>Grimm, Valentin u. a.</b>: LLM-Mediated XAI Explanations: An AI Advisor
    for Fast and Calibrated Judgments on Potential Misinformation, hg. von Balke,
    Wolf-Tilo u. a., New York, USA 2026.'
  van: 'Grimm V, Rubart J, Herder E, Röcker C. LLM-Mediated XAI Explanations: An AI
    Advisor for Fast and Calibrated Judgments on Potential Misinformation. Balke WT,
    Plötzky F, Spaniol M, Herder E, Manikonda L, Liu H, et al., editors. WebSci Companion
    ’26: Companion Publication of the 2026 18th ACM Web Science Conference. New York,
    USA: ACM; 2026.'
conference:
  end_date: 2026-05-26
  location: Braunschweig
  name: 18th ACM Web Science Conference ; WebSci Companion '26
  start_date: 2026-05-26
corporate_editor:
- ACM Press
date_created: 2026-05-05T16:16:34Z
date_updated: 2026-05-27T11:08:52Z
department:
- _id: DEP5023
doi: https://doi.org/10.1145/3795513.3810452
editor:
- first_name: Wolf-Tilo
  full_name: Balke, Wolf-Tilo
  last_name: Balke
- first_name: Florian
  full_name: Plötzky, Florian
  last_name: Plötzky
- first_name: Marc
  full_name: Spaniol, Marc
  last_name: Spaniol
- first_name: Eelco
  full_name: Herder, Eelco
  last_name: Herder
- first_name: Lydia
  full_name: Manikonda, Lydia
  last_name: Manikonda
- first_name: Haiming
  full_name: Liu, Haiming
  last_name: Liu
- first_name: Luis-Daniel
  full_name: Ibáñez, Luis-Daniel
  last_name: Ibáñez
- first_name: Rezvaneh
  full_name: Rezapour, Rezvaneh
  last_name: Rezapour
keyword:
- Large Language Model Mediation
- Explainable AI
- Decision Co- Pilot Systems
- Misinformation Detection
language:
- iso: eng
page: 110-116
place: New York, USA
publication: 'WebSci Companion ''26: Companion Publication of the 2026 18th ACM Web
  Science Conference'
publication_identifier:
  isbn:
  - 979-8-4007-2492-3
publication_status: published
publisher: ACM
quality_controlled: '1'
status: public
title: 'LLM-Mediated XAI Explanations: An AI Advisor for Fast and Calibrated Judgments
  on Potential Misinformation'
type: conference_editor_article
user_id: '83781'
year: '2026'
...