Evaluating Model Alignment with Human Perception: A Study on Shitsukan in LLMs and LVLMs

Daiki Shiono, Ana Brassard, Yukiko Ishizuki, Jun Suzuki


Abstract
We evaluate the alignment of large language models (LLMs) and large vision-language models (LVLMs) with human perception, focusing on the Japanese concept of *shitsukan*, which reflects the sensory experience of perceiving objects. We created a dataset of *shitsukan* terms elicited from individuals in response to object images. With it, we designed benchmark tasks for three dimensions of understanding *shitsukan*: (1) accurate perception in object images, (2) commonsense knowledge of typical *shitsukan* terms for objects, and (3) distinction of valid *shitsukan* terms. Models demonstrated mixed accuracy across benchmark tasks, with limited overlap between model- and human-generated terms. However, manual evaluations revealed that the model-generated terms were still natural to humans. This work identifies gaps in culture-specific understanding and contributes to aligning models with human sensory perception. We publicly release the dataset to encourage further research in this area.
Anthology ID:
2025.coling-main.757
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11428–11444
Language:
URL:
https://aclanthology.org/2025.coling-main.757/
DOI:
Bibkey:
Cite (ACL):
Daiki Shiono, Ana Brassard, Yukiko Ishizuki, and Jun Suzuki. 2025. Evaluating Model Alignment with Human Perception: A Study on Shitsukan in LLMs and LVLMs. In Proceedings of the 31st International Conference on Computational Linguistics, pages 11428–11444, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Evaluating Model Alignment with Human Perception: A Study on Shitsukan in LLMs and LVLMs (Shiono et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.757.pdf