发现大模型推理与记忆的表示方向会随训练改变，但信息仍可解码。
Beyond Fixed Directions: Adaptive Representation Analysis of Reasoning and Memorization in LLMs
- 用单方向投影即可准确区分推理与记忆任务
- 强化学习后方向重排，但分类性能保持100%准确
- 适合关注模型内部表征动态的科研人员
近期研究认为语言模型的推理与记忆可用单一表示方向刻画，且该方向在强化学习中保持固定。本文基于Qwen3-0.6B和400个样本的受控数据集，检验两个假设：第一，推理与事实召回任务是否近似单方向可分？第二，该几何结构在GRPO后是否稳定？结果表明，一维投影可达到1024维线性探测器的性能，AUROC为1.00。然而，在GRPO后，方向发生显著重构：平均方向余弦为0.453，探测方向余弦为0.445，最终层表示漂移达0.511。尽管几何形态改变，探测性能仍维持1.00。证据支持任务组的单方向可解码性，但质疑固定方向的稳定性——信息持续存在，其几何表达却发生变化。
原文摘要 · Abstract (English)
Recent work has proposed that reasoning and memorization in language models can be characterized by a single representation direction, including methods that keep this direction fixed during reinforcement learning. We test two assumptions behind this view. First, are reasoning-oriented and factual-recall task groups approximately single-direction separable? Second, does the resulting geometry remain stable after GRPO? Using Qwen3-0.6B and a controlled 400-example dataset, we find that a one-dimensional projection can match a full 1024-dimensional linear probe with AUROC = 1.00 on the studied task groups. However, after GRPO, the corresponding direction is substantially reorganized: mean-direction cosine averages 0.453, probe-direction cosine 0.445, while direct representation drift reaches 0.511 at the final layer. Probe AUROC nevertheless remains 1.00. The evidence therefore supports single-direction decodability for the studied task groups but challenges fixed-direction stability: the information persists while its geometric realization changes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。