Beyond Pre-Defined Scripts: Player Perceptions on Generative
Non-Player Character Dialogues

D 2026

Beyond Pre-Defined Scripts: Player Perceptions on Generative Non-Player Character Dialogues

HOCHREITER, Manuel; Simone KRIGLSTEIN a Günter WALLNER

Základní údaje

Originální název

Beyond Pre-Defined Scripts: Player Perceptions on Generative Non-Player Character Dialogues

Autoři

HOCHREITER, Manuel; Simone KRIGLSTEIN a Günter WALLNER

Vydání

New York, NY, USA, Proceedings of the 31st International Conference on Intelligent User Interfaces, od s. 2004-2018, 15 s. 2026

Nakladatel

Association for Computing Machinery

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10200 1.2 Computer and information sciences

Stát vydavatele

Spojené státy

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

elektronická verze "online"

Odkazy

URL

Označené pro přenos do RIV

Ano

Organizační jednotka

Fakulta informatiky

ISBN

979-8-4007-1984-4

ISSN

DOI

https://doi.org/10.1145/3742413.3789221

Klíčová slova anglicky

Large Language Models; Non-Player Characters; Dialogue; User Study

Změněno: 27. 3. 2026 11:25, Priv.-Doz. Dipl.-Ing. Dr. Simone Kriglstein

Anotace

V originále

Interactions with non-player characters (NPCs) are ubiquitous in video games but traditionally rely on scripted dialogue. The advent of large language models (LLMs) has opened up new opportunities to converse with NPCs and, in turn, contribute to player experience. However, integrating LLM-driven dialogue in games is not necessarily straightforward and needs an understanding of how this new technique is perceived by players and shapes their game experience. In this paper we contribute to this emerging line of inquiry and report on a study investigating players’ perceptions on LLM-generated dialogues in a bespoke game. Towards this end, we have conducted an online survey, containing both quantitative measures and qualitative open-ended questions, with 62 participants. Our results indicate that LLM-generated dialogues have several benefits such as enhanced input flexibility or leading to more natural conversations but can create a variety of undesired side-effects that might be hard to anticipate beforehand or control for.

Citovat

HOCHREITER, Manuel; Simone KRIGLSTEIN a Günter WALLNER. Beyond Pre-Defined Scripts: Player Perceptions on Generative Non-Player Character Dialogues. Online. In Proceedings of the 31st International Conference on Intelligent User Interfaces. New York, NY, USA: Association for Computing Machinery, 2026, s. 2004-2018. ISBN 979-8-4007-1984-4. Dostupné z: https://doi.org/10.1145/3742413.3789221.

@inproceedings{2563236,
   author = {Hochreiter, Manuel and Kriglstein, Simone and Wallner, Günter},
   address = {New York, NY, USA},
   booktitle = {Proceedings of the 31st International Conference on Intelligent User Interfaces},
   doi = {https://doi.org/10.1145/3742413.3789221},
   keywords = {Large Language Models; Non-Player Characters; Dialogue; User Study},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {New York, NY, USA},
   isbn = {979-8-4007-1984-4},
   pages = {2004-2018},
   publisher = {Association for Computing Machinery},
   title = {Beyond Pre-Defined Scripts: Player Perceptions on Generative Non-Player Character Dialogues},
   url = {https://dl.acm.org/doi/10.1145/3742413.3789221},
   year = {2026}
}

TY  - CONF
ID  - 2563236
AU  - Hochreiter, Manuel - Kriglstein, Simone - Wallner, Günter
PY  - 2026
TI  - Beyond Pre-Defined Scripts: Player Perceptions on Generative Non-Player Character Dialogues
PB  - Association for Computing Machinery
CY  - New York, NY, USA
SN  - 9798400719844
KW  - Large Language Models
KW  - Non-Player Characters
KW  - Dialogue
KW  - User Study
UR  - https://dl.acm.org/doi/10.1145/3742413.3789221
N2  - Interactions with non-player characters (NPCs) are ubiquitous in video games but traditionally rely on scripted dialogue. The advent of large language models (LLMs) has opened up new opportunities to converse with NPCs and, in turn, contribute to player experience. However, integrating LLM-driven dialogue in games is not necessarily straightforward and needs an understanding of how this new technique is perceived by players and shapes their game experience. In this paper we contribute to this emerging line of inquiry and report on a study investigating players’ perceptions on LLM-generated dialogues in a bespoke game. Towards this end, we have conducted an online survey, containing both quantitative measures and qualitative open-ended questions, with 62 participants. Our results indicate that LLM-generated dialogues have several benefits such as enhanced input flexibility or leading to more natural conversations but can create a variety of undesired side-effects that might be hard to anticipate beforehand or control for.
ER  -

HOCHREITER, Manuel; Simone KRIGLSTEIN a Günter WALLNER. Beyond Pre-Defined Scripts: Player Perceptions on Generative Non-Player Character Dialogues. Online. In \textit{Proceedings of the 31st International Conference on Intelligent User Interfaces}. New York, NY, USA: Association for Computing Machinery, 2026, s.~2004-2018. ISBN~979-8-4007-1984-4. Dostupné z: https://doi.org/10.1145/3742413.3789221.

Přehled o publikaci