arXiv cs.AI· Okan S. Coskun, Florian Rottach, Carsten Eickhoff, William Rudman·· 1 天前AI 评分26
各向同性悬崖：大语言模型决策过程的几何特征
Isotropy Cliffs: The Geometric Signature of Decision-Making in Large Language Models
AI 导读
研究从各向同性视角分析五个开放权重模型在多项选择问答中的决策几何，发现存在各向同性发生转变的决策关键过渡层，该层伴随显著表征变化与任务相关簇的出现。这一几何行为与下游准确率强相关（r≈0.84），且对提示词变化保持稳健，表明其反映模型行为的通用机制。
正文 · 原文
Abstract:We investigate the geometry of decision-making in Multiple Choice Question Answering (MCQA) through the lens of isotropy. Analyzing five open-weight models across diverse datasets, we identify decision-critical transition layers characterized by a shift in isotropy, coinciding with a major representational change and the emergence of task-relevant clusters. We demonstrate that this synchronized geometric behavior is strongly correlated with downstream accuracy ($r\approx0.84$), displaying its relevance for successful decision-making. Furthermore, we show that this transition is robust to prompt variations, suggesting that it reflects a general mechanism of model behavior.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2608.00828 [cs.AI] |
| (or arXiv:2608.00828v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2608.00828 arXiv-issued DOI via DataCite |
Submission history
From: Okan Selim Coskun [view email]
[v1]
Sat, 1 Aug 2026 19:11:10 UTC (2,927 KB)
[v2]
Wed, 11 Nov 2026 15:45:01 UTC (2,989 KB)
来源：arXiv cs.AI · arxiv.org