37.2473, Confs: Panel at IPC20: Human Creative Practices in Interaction with LLM-based Assistants (Finland)

[The LINGUIST List]

LINGUIST List: Vol-37-2473. Fri Jul 24 2026. ISSN: 1069 - 4875.

Subject: 37.2473, Confs: Panel at IPC20: Human Creative Practices in Interaction with LLM-based Assistants (Finland)

Moderator: Steven Moran (linguist at linguistlist.org)
Managing Editor: Valeriia Vyshnevetska
Team: Helen Aristar-Dry, Mara Baccaro, Daniel Swanson
Jobs: jobs at linguistlist.org | Conferences: callconf at linguistlist.org | Pubs: pubs at linguistlist.org

Homepage: http://linguistlist.org

Editor for this issue: Valeriia Vyshnevetska <valeriia at linguistlist.org>

================================================================


Date: 23-Jul-2026
From: Clara Lachenmaier [clara.lachenmaier at uni-bielefeld.de]
Subject: Panel at IPC20: Human Creative Practices in Interaction with LLM-based Assistants


Panel at IPC20: Human Creative Practices in Interaction with LLM-based
Assistants

Date: 25-Jun-2027 - 02-Jul-2027
Location: Helsinki, Finland

Linguistic Field(s): Pragmatics

Submission Deadline: 15-Oct-2026

Topics: AI, Robotics, Technology; Anthropological Linguistics and
Ethnography; Conversation Analysis/EMCA; Interactional Pragmatics
Abstract: Assistants based on large language models (LLMs) have
achieved remarkable uptake as a new medium advertised as
conversational partners. They may be marketed as companions
(Malfacini, 2025) for therapy (Scholich et al., 2025), used for
programming, research, and writing (Haase et al., 2026), and a variety
of other purposes. On the surface, such assistants present as fluent,
responsive, and contextually aware in written and increasingly in
spoken conversation. Yet beneath this appearance lies a fundamental
asymmetry: LLM-based chatbots do not interact the way humans do and
this in turn influences how we interact with them. Due to engineering
decisions, selection of training data, reinforcement learning from
human feedback (RLHF), installation of guardrails, design objectives
to comply, and fundamental issues these models tend to hallucinate (Ji
et al., 2023), over-accommodate (Lachenmaier et al., 2025), or show
sycophantic behaviour (Wang et al., 2026). Empirical work both in
computational linguistics as well as ethnomethodology and conversation
analysis (Stokoe et al., 2024) has begun to demonstrate that, at the
interactional level, human–LLM exchanges deviate systematically from
human interaction, e.g., in how communicative trouble is handled (Pütz
and Esposito, 2024; Lachenmaier et al., 2026) or how the interaction
is contextualized (Pütz, 2026).
Recent studies have shown that some of these limitations can be
circumvented by changing wording or grammatical structure of prompts
(Wang et al., 2026). Due to the models’ black-box nature, however,
such strategies cannot be introduced systematically (Dingemanse, to
appear), but must be discovered by users in an explorative way, making
use of the human ability of being linguistically creative (Vogel et
al., 2026). For this panel, we seek interdisciplinary contributions
from the fields of computational pragmatics, interactional pragmatics,
ethnomethodology and conversation analysis, presenting empirical
results on human creative practices in interaction with LLM-based
chatbots or voice assistants. The focus of the panel is on how users
overcome the above mentioned limitations, restrictions, and pitfalls,
by adapting their communication techniques to the chatbots’
characteristics. For example, how do they formulate prompts and
messages to chatbots (e.g., by engaging in role play, flouting
pragmatic maxims, deceiving, being (im-)polite)? More generally, how
do they invent and disseminate practices that probe and exploit
models’ affordances and peculiarities?
Please submit your abstract (up to 500 words, including references)
via the conference website (https://ipra2027.exordo.com/) by 15
October 2026. In step 4 (‘Topics’) of the submission process, select
the panel ‘Human Creative Practices . . . ’. Further information on
submitting abstracts can be found in the IPC20 Call for Papers
(https://pragmatics.international/page/CfP2027). Please note that an
active IPrA membership for at least the first author is required to
submit an abstract.
If you have any further questions regarding the panel, please feel
free to contact us directly:
 - Hendrik Buschmeier: Digital Linguistics Lab, Department of
Linguistics, Bielefeld University, hbuschme at uni-bielefeld.de
 - Clara Lachenmaier: Computational Linguistics, Department of
Linguistics, Bielefeld University, clara.lachenmaier at uni-bielefeld.de
 - Ole Pütz: Semantic Computing Group, Faculty of Technology,
Bielefeld University, ole.puetz at uni-bielefeld.de
 - Birte Schaller: Language and Communication, Department of
Linguistics, Bielefeld University, birte.schaller at uni-bielefeld.de
References:
Mark Dingemanse. to appear. Interactional foundations for critical AI
literacies. In Ana Valdivia, editor, A Research Agenda for Critical
AI. Zenodo (preprint).
Jennifer Haase, Florian Butollo, Konrad-Malte Hoppe, Ann-Katrin
Katzinski, and Anne K. Krüger. 2026. ChatGPT in knowledge-intensive
work: Patterns of adoption, perceived usefulness, and human-ai
collaboration across three domains. International Journal of
Technology Diffusion, 16(1):1–22.
Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu,
Etsuko Ishii, Ye Jin Bang, Andrea Madotto, and Pascale Fung. 2023.
Survey of hallucination in natural language generation. ACM Computing
Surveys, 55(12):248:1–38.
Clara Lachenmaier, Hannah Bultmann, and Sina Zarrieß. 2026. Talking to
a know-it-all GPT or a secondguesser Claude? How repair reveals
distinct multi-turn behavior in LLMs. In Proceedings of the 64th
Annual Meeting of the Association for Computational Linguistics, pages
14312–14325, San Diego, CA, USA. ACL.
Clara Lachenmaier, Judith Sieker, and Sina Zarrieß. 2025. Can LLMs
ground when they (don’t) know: A study on direct and loaded political
questions. In Proceedings of the 63rd Annual Meeting of the
Association for Computational Linguistics, pages 14956–14975, Vienna,
Austria. ACL.
Kim Malfacini. 2025. The impacts of companion AI on human
relationships: Risks, benefits, and design considerations. AI &
Society, 40:5527–5540.
Ole Pütz and Elena Esposito. 2024. Performance without understanding:
How ChatGPT relies on humans to repair conversational trouble.
Discourse & Communication, 18(6):859–868.
Ole Pütz. 2026. Co-textual dopes: How LLMs produce contextually
appropriate text in chat interactions with humans without access to
context. Journal of Linguistic Anthropology, 36(1):e70036.
Till Scholich, Maya Barr, Shannon Wiltsey Stirman, and Shriti Raj.
2025. A comparison of responses from human therapists and large
language model–based chatbots to assess therapeutic communication:
Mixed methods study. JMIR Ment Health, 12:e69709.
Elizabeth Stokoe, Saul Albert, Hendrik Buschmeier, and Wyke Stommel.
2024. Conversation analysis and conversational technologies: Finding
the common ground between academia and industry. Discourse &
Communication, 18(6):837–847.
Ralf Vogel, Joana Cholin, Jutta Hartmann, Oliver Bott, Jana Häussler,
Torgrim Solstad, Petra Wagner, Sina Zarrieß, Tanja Ackermann, András
Bárány, Carola de Beer, Hendrik Buschmeier, Berenike Herrmann, Martina
Hielscher-Fastabend, Farhat Jabeen, Barbara Job, Annett Jorschick,
Johanna Kißler, Heike Knerich, and 12 others. 2026. Linguistic
creativity in communication. Conceptions and challenges. LINCC Working
Paper 1, Bielefeld University, Bielefeld, Germany.
Keyu Wang, Jin Li, Shu Yang, Zhuoran Zhang, and Di Wang. 2026. When
truth is overridden: Uncovering the internal origins of sycophancy in
large language models. Proceedings of the AAAI Conference on
Artificial Intelligence, 40(39):33566–33574.



------------------------------------------------------------------------------

********************** LINGUIST List Support ***********************
Please consider donating to the Linguist List, a U.S. 501(c)(3) not for profit organization:

https://www.paypal.com/donate/?hosted_button_id=87C2AXTVC4PP8

LINGUIST List is supported by the following publishers:

Australian Linguistics Society https://als.asn.au/Home

Bloomsbury Publishing http://www.bloomsbury.com/uk/

Cambridge University Press http://www.cambridge.org/linguistics

Cascadilla Press http://www.cascadilla.com/

De Gruyter Brill https://www.degruyterbrill.com/?changeLang=en

Edinburgh University Press http://www.edinburghuniversitypress.com

John Benjamins http://www.benjamins.com/

Language Science Press http://langsci-press.org

Lincom GmbH https://lincom-shop.eu/

MIT Press http://mitpress.mit.edu/

Multilingual Matters http://www.multilingual-matters.com/

Narr Francke Attempto Verlag GmbH + Co. KG http://www.narr.de/

Netherlands Graduate School of Linguistics / Landelijke (LOT) http://www.lotpublications.nl/

Peter Lang AG http://www.peterlang.com

SIL International Publications http://www.sil.org/resources/publications


----------------------------------------------------------
LINGUIST List: Vol-37-2473
----------------------------------------------------------