@inproceedings{qin-etal-2025-overview,
title = "Overview of {CCL}25-Eval Task 1: The Fifth Spatial Cognition Evaluation ({S}pa{CE}2025)",
author = "Qin, Yuhang and
Xiao, Liming and
Hu, Nan and
Deng, Sirui and
Ma, Jingyuan and
Cui, Hyang and
Zhang, Zihan and
Tsai, Chi Hsu and
Ding, Jinkun and
Kang, Sumin and
Sui, Zhifang and
Zhan, Weidong",
editor = "Lin, Hongfei and
Li, Bin and
Tan, Hongye",
booktitle = "Proceedings of the 24th {C}hina National Conference on Computational Linguistics ({CCL} 2025)",
month = aug,
year = "2025",
address = "Jinan, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2025.ccl-2.4/",
pages = "33--46",
abstract = "``The Fifth Spatial Cognition Evaluation (SpaCE2025) presents a benchmark aimed at evaluating the spatial semantic understanding and reasoning capabilities of Large Language Models(LLMs), primarily in Chinese.It consists of five subtasks: (1) Retrieving Spatial Referents(RSR), (2) Detecting Spatial Semantic Anomalies (DSA), (3) Recognizing Synonymous SpatialExpression (RSE), (4) Spatial Position Reasoning (SPR) in Chinese, and (5) SPR in English. The fourth and fifth subtask share the same content and structure, differing only in language, and are designed to assess the cross-linguistic spatial reasoning capability of LLMs. A total of 12 teams submitted their final results, and the best-performing team achieved an accuracy of 0.7931. The results suggest that while LLMs are capable of handling basic spatial semantic understanding tasks such as RSR, their performance on more complex tasks, such as DSA and RSE, still re-quires improvement. Additionally, finetuning methods that effectively activate LLMs' reasoning ability are essential to improve their performance.''"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qin-etal-2025-overview">
<titleInfo>
<title>Overview of CCL25-Eval Task 1: The Fifth Spatial Cognition Evaluation (SpaCE2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuhang</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liming</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nan</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sirui</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingyuan</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyang</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zihan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chi</namePart>
<namePart type="given">Hsu</namePart>
<namePart type="family">Tsai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinkun</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sumin</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhifang</namePart>
<namePart type="family">Sui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weidong</namePart>
<namePart type="family">Zhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th China National Conference on Computational Linguistics (CCL 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongfei</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongye</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Jinan, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>“The Fifth Spatial Cognition Evaluation (SpaCE2025) presents a benchmark aimed at evaluating the spatial semantic understanding and reasoning capabilities of Large Language Models(LLMs), primarily in Chinese.It consists of five subtasks: (1) Retrieving Spatial Referents(RSR), (2) Detecting Spatial Semantic Anomalies (DSA), (3) Recognizing Synonymous SpatialExpression (RSE), (4) Spatial Position Reasoning (SPR) in Chinese, and (5) SPR in English. The fourth and fifth subtask share the same content and structure, differing only in language, and are designed to assess the cross-linguistic spatial reasoning capability of LLMs. A total of 12 teams submitted their final results, and the best-performing team achieved an accuracy of 0.7931. The results suggest that while LLMs are capable of handling basic spatial semantic understanding tasks such as RSR, their performance on more complex tasks, such as DSA and RSE, still re-quires improvement. Additionally, finetuning methods that effectively activate LLMs’ reasoning ability are essential to improve their performance.”</abstract>
<identifier type="citekey">qin-etal-2025-overview</identifier>
<location>
<url>https://aclanthology.org/2025.ccl-2.4/</url>
</location>
<part>
<date>2025-08</date>
<extent unit="page">
<start>33</start>
<end>46</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Overview of CCL25-Eval Task 1: The Fifth Spatial Cognition Evaluation (SpaCE2025)
%A Qin, Yuhang
%A Xiao, Liming
%A Hu, Nan
%A Deng, Sirui
%A Ma, Jingyuan
%A Cui, Hyang
%A Zhang, Zihan
%A Tsai, Chi Hsu
%A Ding, Jinkun
%A Kang, Sumin
%A Sui, Zhifang
%A Zhan, Weidong
%Y Lin, Hongfei
%Y Li, Bin
%Y Tan, Hongye
%S Proceedings of the 24th China National Conference on Computational Linguistics (CCL 2025)
%D 2025
%8 August
%I Chinese Information Processing Society of China
%C Jinan, China
%F qin-etal-2025-overview
%X “The Fifth Spatial Cognition Evaluation (SpaCE2025) presents a benchmark aimed at evaluating the spatial semantic understanding and reasoning capabilities of Large Language Models(LLMs), primarily in Chinese.It consists of five subtasks: (1) Retrieving Spatial Referents(RSR), (2) Detecting Spatial Semantic Anomalies (DSA), (3) Recognizing Synonymous SpatialExpression (RSE), (4) Spatial Position Reasoning (SPR) in Chinese, and (5) SPR in English. The fourth and fifth subtask share the same content and structure, differing only in language, and are designed to assess the cross-linguistic spatial reasoning capability of LLMs. A total of 12 teams submitted their final results, and the best-performing team achieved an accuracy of 0.7931. The results suggest that while LLMs are capable of handling basic spatial semantic understanding tasks such as RSR, their performance on more complex tasks, such as DSA and RSE, still re-quires improvement. Additionally, finetuning methods that effectively activate LLMs’ reasoning ability are essential to improve their performance.”
%U https://aclanthology.org/2025.ccl-2.4/
%P 33-46
Markdown (Informal)
[Overview of CCL25-Eval Task 1: The Fifth Spatial Cognition Evaluation (SpaCE2025)](https://aclanthology.org/2025.ccl-2.4/) (Qin et al., CCL 2025)
ACL
- Yuhang Qin, Liming Xiao, Nan Hu, Sirui Deng, Jingyuan Ma, Hyang Cui, Zihan Zhang, Chi Hsu Tsai, Jinkun Ding, Sumin Kang, Zhifang Sui, and Weidong Zhan. 2025. Overview of CCL25-Eval Task 1: The Fifth Spatial Cognition Evaluation (SpaCE2025). In Proceedings of the 24th China National Conference on Computational Linguistics (CCL 2025), pages 33–46, Jinan, China. Chinese Information Processing Society of China.