The Fourth Evaluation on Chinese Spatial Cognition

Xiao Liming, Hu Nan, Zhan Weidong, Qin Yuhang, Deng Sirui, Sun Chunhui, Cai Qixu, Li Nan


Abstract
“The Fourth Chinese Spatial Cognition Evaluation Task (SpaCE 2024) presents the first comprehensive Chinese benchmark to assess spatial semantic understanding and reasoning capabilities of Large Language Models (LLMs). It comprises five subtasks in the form of multiple-choice questions: (1) identifying spatial semantic roles; (2) retrieving spatial referents; (3) detecting spatial semantic anomalies; (4) recognizing synonymous spatial expression with different forms; (5) conducting spatial position reasoning. In addition to proposing new tasks, SpaCE 2024 applied a rule-based method to generate high-quality synthetic data with difficulty levels for the reasoning task. 12 teams submitted their models and results, and the top-performing team attained an accuracy of 60.24%, suggesting that there is still significant room for current LLMs to improve, especially in tasks requiring high spatial cognitive processing.”
Anthology ID:
2024.ccl-3.14
Volume:
Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations)
Month:
July
Year:
2024
Address:
Taiyuan, China
Editors:
Hongfei Lin, Hongye Tan, Bin Li
Venue:
CCL
SIG:
Publisher:
Chinese Information Processing Society of China
Note:
Pages:
122–134
Language:
English
URL:
https://aclanthology.org/2024.ccl-3.14/
DOI:
Bibkey:
Cite (ACL):
Xiao Liming, Hu Nan, Zhan Weidong, Qin Yuhang, Deng Sirui, Sun Chunhui, Cai Qixu, and Li Nan. 2024. The Fourth Evaluation on Chinese Spatial Cognition. In Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 3: Evaluations), pages 122–134, Taiyuan, China. Chinese Information Processing Society of China.
Cite (Informal):
The Fourth Evaluation on Chinese Spatial Cognition (Liming et al., CCL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.ccl-3.14.pdf