更多未必更好：对视觉空间推理中空间与常识信息的系统分析
When More Is Less: A Systematic Analysis of Spatial and Commonsense Information for Visual Spatial Reasoning
AI总结：
本文通过系统分析发现，过多信息未必提升视觉空间推理性能，针对性单空间提示和精确空间定位可提高准确性。
摘要：
视觉空间推理（VSR）仍然是现代视觉-语言模型（VLMs）面临的挑战，尽管多模态架构取得了进展。一种常见策略是在推理时注入额外信息，例如显式的空间提示、外部常识知识或推理链（CoT）提示。然而，仍然不清楚何时此类信息真正提升推理能力，何时引入噪声。在本文中，我们针对三个代表性的VLMs和两个公开基准进行假设驱动的分析。我们考察（i）空间上下文的类型和数量，（ii）注入常识知识的量和相关性，以及（iii）空间定位与CoT提示的交互。我们的结果揭示了一种一致模式：更多信息并不一定带来更好的推理。针对性的单一空间提示优于多上下文聚合，过多或弱相关的常识知识会降低性能，而CoT提示只有在空间定位足够精确时才能提高准确性。这些发现强调了选择性、任务对齐的信息注入的重要性，并为设计可靠的多模态推理管道提供了实用指导。
英文摘要：
Visual spatial reasoning (VSR) remains challenging for modern vision-language models (VLMs), despite advances in multimodal architectures. A common strategy is to inject additional information at inference time, such as explicit spatial cues, external commonsense knowledge, or chain-of-thought (CoT) reasoning instructions. However, it remains unclear when such information genuinely improves reasoning and when it introduces noise. In this paper, we conduct a hypothesis-driven analysis of information injection for VSR across three representative VLMs and two public benchmarks. We examine (i) the type and number of spatial contexts, (ii) the amount and relevance of injected commonsense knowledge, and (iii) the interaction between spatial grounding and CoT prompting. Our results reveal a consistent pattern: more information does not necessarily yield better reasoning. Targeted single spatial cues outperform multi-context aggregation, excessive or weakly relevant commonsense knowledge degrades performance, and CoT prompting improves accuracy only when spatial grounding is sufficiently precise. These findings highlight the importance of selective, task-aligned information injection and provide practical guidance for designing reliable multimodal reasoning pipelines.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
