Over the past year, spatial intelligence has drawn increasing attention. Many prior works study it from the perspective of visual-spatial intelligence, where models have access to visuospatial information from visual inputs. However, in the absence of visual information, whether linguistic intelligence alone is sufficient to endow models with spatial intelligence, and how models perform relevant tasks with text-only inputs still remain unexplored. Therefore, in this paper, we focus on a fundamental and critical capability in spatial intelligence from a linguistic perspective: viewpoint rotation understanding (VRU). Specifically, LLMs and VLMs are asked to infer their final viewpoint and predict the corresponding observation in an environment given textual description of viewpoint rotation and observation over multiple steps. We find that both LLMs and VLMs perform poorly on our proposed dataset while human can easily achieve 100% accuracy, indicating a substantial gap between current model capabilities and the requirements of spatial intelligence. To uncover the underlying mechanisms, we conduct a layer-wise probing analysis and head-wise causal intervention. Our findings reveal that although models encode viewpoint information in the hidden states, they appear to struggle to bind the viewpoint position with corresponding observation, resulting in a hallucination in final layers. Finally, we selectively fine-tune the key attention heads identified by causal intervention to improve VRU performance. Experimental results demonstrate that such selective fine-tuning achieves improved VRU performance while avoiding catastrophic forgetting of generic abilities.

“Chinese Frame Semantic Parsing (CFSP) is an important task in the field of Chinese Natural Language Processing(NLP). Its goal is to extract the frame semantic structure from the sentence and realize the deep understanding of the events or situations involved in the sentence. This paper mainly studies the application of Large Language Model (LLM) for reasoning through Prompt Engineering without fine-tuning the model, and completes three subtasks of Chinese Framework Semantic Parsing tasks: frame identification, argument Identification and role identification. This paper proposes a Retrieval Augmented Generation (RAG) method for target words, and constructs more refined sample Few-Shot method. We achieved the second place on the B rankings in the open track in the “CCL2024-Eval The Second Chinese Frame Semantic Parsing”competition*.”