Advanced search
2 files | 3.31 MB Add to list

Word synchronization challenge : a benchmark for word association responses for large language models

Tanguy Cazalets (UGent) and Joni Dambre (UGent)
Author
Organization
Abstract
This paper introduces the Word Synchronization Challenge, a novel benchmark to evaluate large language models (LLMs) in Human-Computer Interaction (HCI). This benchmark utilizes a dynamic game-like framework to test LLMs’ ability to mimic human cognitive processes through word associations. By simulating complex human interactions, it assesses how LLMs interpret and align with human thought patterns during conversational exchanges, essential for effective social partnerships in HCI. Initial findings highlight the influence of model sophistication on performance, offering insights into the models’ capabilities to engage in meaningful social interactions and adapt behaviors in human-like manners. This research advances understanding of LLMs’ potential to replicate or diverge from human cognitive functions, paving the way for more nuanced and empathetic human-machine collaborations.
Keywords
Human Centered AI (HCAI), Explainable AI (XAI), Benchmark, Theory of Mind, Word associations

Downloads

  • (...).pdf
    • full text (Accepted manuscript)
    • |
    • UGent only (changes to open access on 2026-06-05)
    • |
    • PDF
    • |
    • 1.29 MB
  • (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 2.03 MB

Citation

Please use this url to cite or link to this publication:

MLA
Cazalets, Tanguy, and Joni Dambre. “Word Synchronization Challenge : A Benchmark for Word Association Responses for Large Language Models.” HUMAN-COMPUTER INTERACTION, HCI 2025, PT V, edited by Masaaki Kurosu and Ayako Hashizume, vol. 15770, Springer, 2025, pp. 3–19, doi:10.1007/978-3-031-93864-1_1.
APA
Cazalets, T., & Dambre, J. (2025). Word synchronization challenge : a benchmark for word association responses for large language models. In M. Kurosu & A. Hashizume (Eds.), HUMAN-COMPUTER INTERACTION, HCI 2025, PT V (Vol. 15770, pp. 3–19). https://doi.org/10.1007/978-3-031-93864-1_1
Chicago author-date
Cazalets, Tanguy, and Joni Dambre. 2025. “Word Synchronization Challenge : A Benchmark for Word Association Responses for Large Language Models.” In HUMAN-COMPUTER INTERACTION, HCI 2025, PT V, edited by Masaaki Kurosu and Ayako Hashizume, 15770:3–19. Springer. https://doi.org/10.1007/978-3-031-93864-1_1.
Chicago author-date (all authors)
Cazalets, Tanguy, and Joni Dambre. 2025. “Word Synchronization Challenge : A Benchmark for Word Association Responses for Large Language Models.” In HUMAN-COMPUTER INTERACTION, HCI 2025, PT V, ed by. Masaaki Kurosu and Ayako Hashizume, 15770:3–19. Springer. doi:10.1007/978-3-031-93864-1_1.
Vancouver
1.
Cazalets T, Dambre J. Word synchronization challenge : a benchmark for word association responses for large language models. In: Kurosu M, Hashizume A, editors. HUMAN-COMPUTER INTERACTION, HCI 2025, PT V. Springer; 2025. p. 3–19.
IEEE
[1]
T. Cazalets and J. Dambre, “Word synchronization challenge : a benchmark for word association responses for large language models,” in HUMAN-COMPUTER INTERACTION, HCI 2025, PT V, Gothenburg, Sweden, 2025, vol. 15770, pp. 3–19.
@inproceedings{01JVW243A2466QF51W74JW9DEH,
  abstract     = {{This paper introduces the Word Synchronization Challenge, a novel benchmark to evaluate large language models (LLMs) in Human-Computer Interaction (HCI). This benchmark utilizes a dynamic game-like framework to test LLMs’ ability to mimic human cognitive processes through word associations. By simulating complex human interactions, it assesses how LLMs interpret and align with human thought patterns during conversational exchanges, essential for effective social partnerships in HCI. Initial findings highlight the influence of model sophistication on performance, offering insights into the models’ capabilities to engage in meaningful social interactions and adapt behaviors in human-like manners. This research advances understanding of LLMs’ potential to replicate or diverge from human cognitive functions, paving the way for more nuanced and empathetic human-machine collaborations.}},
  author       = {{Cazalets, Tanguy and Dambre, Joni}},
  booktitle    = {{HUMAN-COMPUTER INTERACTION, HCI 2025, PT V}},
  editor       = {{Kurosu, Masaaki and Hashizume, Ayako}},
  isbn         = {{9783031938634}},
  issn         = {{0302-9743}},
  keywords     = {{Human Centered AI (HCAI),Explainable AI (XAI),Benchmark,Theory of Mind,Word associations}},
  language     = {{eng}},
  location     = {{Gothenburg, Sweden}},
  pages        = {{3--19}},
  publisher    = {{Springer}},
  title        = {{Word synchronization challenge : a benchmark for word association responses for large language models}},
  url          = {{http://doi.org/10.1007/978-3-031-93864-1_1}},
  volume       = {{15770}},
  year         = {{2025}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: