"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."

“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.”

“第二届中文空间语义理解评测任务(SpaCE2022)旨在测试机器的空间语义理解能力,包括三个子任务:(1)中文空间语义正误判断任务;(2)中文空间语义异常归因与异常文本识别任务;(3)中文空间实体识别与空间方位关系标注任务。本文围绕SpaCE2022数据集介绍了标注规范和数据集制作流程,总结了改善数据集质量的方法,包括构建STEP标注体系,规范描述空间语义信息;基于语言学知识生成空间异常句子,提高数据多样性;采取双人标注、基于规则的实时质检、人工抽样审核等方式加强数据质量控制;分级管理标注数据,优选高质量数据进入数据集。通过考察数据集分布情况以及机器表现和人类表现,本文发现SpaCE2022数据集的标签分布存在明显偏差,而且正误判断任务和异常归因任务的主观性强,一致性低,这些问题有待在将来的SpaCE任务设计中做进一步优化。”

“第三届中文空间语义理解评测任务(SpaCE2023)旨在测试机器的空间语义理解能力,包括三个子任务:(1)空间信息异常识别任务;(2)空间语义角色标注任务;(3)空间场景异同判断任务。本届评测在SpaCE2022的基础上,优化了子任务一和子任务二的任务设计,并提出了子任务三这一全新的评测任务。最终有1支队伍提交参赛结果,并且在子任务一上的成绩超过了基线模型。本文还报告了大语言模型ChatGPT在SpaCE2023三个子任务上的表现,结合问题提出指令设计可改进的方向。”

It is a common practice for recent works in vision language cross-modal reasoning to adopt a binary or multi-choice classification formulation taking as input a set of source image(s) and textual query. In this work, we take a sober look at such an “unconditional” formulation in the sense that no prior knowledge is specified with respect to the source image(s). Inspired by the designs of both visual commonsense reasoning and natural language inference tasks, we propose a new task termed “Premise-based Multi-modal Reasoning” (PMR) where a textual premise is the background presumption on each source image. The PMR dataset contains 15,360 manually annotated samples which are created by a multi-phase crowd-sourcing process. With selected high-quality movie screenshots and human-curated premise templates from 6 pre-defined categories, we ask crowd-source workers to write one true hypothesis and three distractors (4 choices) given the premise and image through a cross-check procedure.