Human alignment : how much do we adapt to LLMs?
- Author
- Tanguy Cazalets (UGent) , Ruben Janssens (UGent) , Tony Belpaeme (UGent) and Joni Dambre (UGent)
- Organization
- Abstract
- Large Language Models (LLMs) are becoming a common part of our lives, yet few studies have examined how they influence our behavior. Using a cooperative language game in which players aim to converge on a shared word, we investigate how people adapt their communication strategies when paired with either an LLM or another human. Our study demonstrates that LLMs exert a measurable influence on human communication strategies and that humans notice and adapt to these differences irrespective of whether they are aware they are interacting with an LLM. These findings highlight the reciprocal influence of human{--}AI dialogue and raise important questions about the long-term implications of embedding LLMs in everyday communication.
- Keywords
- COORDINATION
Downloads
-
(...).pdf
- full text (Published version)
- |
- UGent only
- |
- |
- 1.38 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-01K1G6E06EGDSYY7MTFZYHYFZN
- MLA
- Cazalets, Tanguy, et al. “Human Alignment : How Much Do We Adapt to LLMs?” PROCEEDINGS OF THE 63RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 2 : SHORT PAPERS, edited by Wanxiang Che et al., Association for Computational Linguistics (ACL), 2025, pp. 603–13, doi:10.18653/v1/2025.acl-short.47.
- APA
- Cazalets, T., Janssens, R., Belpaeme, T., & Dambre, J. (2025). Human alignment : how much do we adapt to LLMs? In W. Che, J. Nabende, E. Shutova, & M. Taher Pilehvar (Eds.), PROCEEDINGS OF THE 63RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 2 : SHORT PAPERS (pp. 603–613). https://doi.org/10.18653/v1/2025.acl-short.47
- Chicago author-date
- Cazalets, Tanguy, Ruben Janssens, Tony Belpaeme, and Joni Dambre. 2025. “Human Alignment : How Much Do We Adapt to LLMs?” In PROCEEDINGS OF THE 63RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 2 : SHORT PAPERS, edited by Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar, 603–13. Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2025.acl-short.47.
- Chicago author-date (all authors)
- Cazalets, Tanguy, Ruben Janssens, Tony Belpaeme, and Joni Dambre. 2025. “Human Alignment : How Much Do We Adapt to LLMs?” In PROCEEDINGS OF THE 63RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 2 : SHORT PAPERS, ed by. Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar, 603–613. Association for Computational Linguistics (ACL). doi:10.18653/v1/2025.acl-short.47.
- Vancouver
- 1.Cazalets T, Janssens R, Belpaeme T, Dambre J. Human alignment : how much do we adapt to LLMs? In: Che W, Nabende J, Shutova E, Taher Pilehvar M, editors. PROCEEDINGS OF THE 63RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 2 : SHORT PAPERS. Association for Computational Linguistics (ACL); 2025. p. 603–13.
- IEEE
- [1]T. Cazalets, R. Janssens, T. Belpaeme, and J. Dambre, “Human alignment : how much do we adapt to LLMs?,” in PROCEEDINGS OF THE 63RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 2 : SHORT PAPERS, Vienna, Austria, 2025, pp. 603–613.
@inproceedings{01K1G6E06EGDSYY7MTFZYHYFZN,
abstract = {{Large Language Models (LLMs) are becoming a common part of our lives, yet few studies have examined how they influence our behavior. Using a cooperative language game in which players aim to converge on a shared word, we investigate how people adapt their communication strategies when paired with either an LLM or another human. Our study demonstrates that LLMs exert a measurable influence on human communication strategies and that humans notice and adapt to these differences irrespective of whether they are aware they are interacting with an LLM. These findings highlight the reciprocal influence of human{--}AI dialogue and raise important questions about the long-term implications of embedding LLMs in everyday communication.}},
author = {{Cazalets, Tanguy and Janssens, Ruben and Belpaeme, Tony and Dambre, Joni}},
booktitle = {{PROCEEDINGS OF THE 63RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 2 : SHORT PAPERS}},
editor = {{Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Taher Pilehvar, Mohammad}},
isbn = {{9798891762527}},
keywords = {{COORDINATION}},
language = {{eng}},
location = {{Vienna, Austria}},
pages = {{603--613}},
publisher = {{Association for Computational Linguistics (ACL)}},
title = {{Human alignment : how much do we adapt to LLMs?}},
url = {{http://doi.org/10.18653/v1/2025.acl-short.47}},
year = {{2025}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: