从人类认知到神经激活：探究LLMs中空间推理的计算原语
From Human Cognition to Neural Activations: Probing the Computational Primitives of Spatial Reasoning in LLMs
AI总结：
研究通过分析LLMs内部空间表示机制，发现其空间推理能力有限且依赖上下文，揭示了空间推理的计算原语及跨语言机制退化问题。
摘要：
随着空间智能在基础模型中的重要性提升，仍不清楚大语言模型（LLMs）在空间推理基准上的表现是反映结构化的内部空间表示还是依赖语言启发式。我们从机械角度出发，探讨空间信息如何被内部表示和使用。基于人类空间认知的计算理论，我们将空间推理分解为三个原语：关系组合、表示转换和状态空间更新，并为每个原语设计受控任务族。我们评估了英语、中文和阿拉伯语多语言LLMs在单次推理下的表现，并利用线性探测、基于稀疏自动编码器的特征分析和因果干预分析内部表示。我们发现任务相关的空间信息编码在中间层，并能因果影响行为，但这些表示是短暂的、在不同任务族中碎片化且弱整合到最终预测中。跨语言分析进一步揭示了机制退化，相似的行为表现源于不同的内部路径。总体而言，我们的结果表明当前LLMs表现出有限且依赖上下文的空间表示，而非稳健、通用的空间推理，突显了超越基准准确性的机械评估需求。
英文摘要：
As spatial intelligence becomes an increasingly important capability for foundation models, it remains unclear whether large language models' (LLMs) performance on spatial reasoning benchmarks reflects structured internal spatial representations or reliance on linguistic heuristics. We address this question from a mechanistic perspective by examining how spatial information is internally represented and used. Drawing on computational theories of human spatial cognition, we decompose spatial reasoning into three primitives, relational composition, representational transformation, and stateful spatial updating, and design controlled task families for each. We evaluate multilingual LLMs in English, Chinese, and Arabic under single pass inference, and analyze internal representations using linear probing, sparse autoencoder based feature analysis, and causal interventions. We find that task relevant spatial information is encoded in intermediate layers and can causally influence behavior, but these representations are transient, fragmented across task families, and weakly integrated into final predictions. Cross linguistic analysis further reveals mechanistic degeneracy, where similar behavioral performance arises from distinct internal pathways. Overall, our results suggest that current LLMs exhibit limited and context dependent spatial representations rather than robust, general purpose spatial reasoning, highlighting the need for mechanistic evaluation beyond benchmark accuracy.
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。
