发现语言模型中规划信号的形成位置及因果作用，揭示不同模型的生成机制差异。
Where's the Plan? Locating Latent Planning in Language Models with Lightweight Mechanistic Interventions
- 通过轻量干预法定位未来韵律信息在模型中的编码位置。
- 仅Gemma-3-27B在第30层左右出现规划信号的因果转移。
- 该模型通过5个注意力头实现韵律信息的高效传递，适合研究生成机制者关注。
我们研究语言模型中的规划信号形成——即结构化未来词元的内部表征在前向传播中何时产生，以及是否具有因果驱动作用。以押韵对句补全为纯净的前瞻约束测试任务，我们在Qwen3、Gemma-3和Llama-3三个系列超过十个规模上应用线性探测与激活修补两种轻量方法。探测结果显示，未来押韵信息在句边界处可线性解码，且信号强度随模型规模提升，在所有三类模型中均成立。激活修补揭示，仅Gemma-3-27B依赖此编码，表现出因果驱动从押韵词向句边界迁移的现象，约在第30层发生；其余模型全程依赖押韵词，尽管探测信号强，但在句边界处因果效应几乎为零。通过两阶段路径修补，将该迁移定位至5个注意力头，恢复了约90%的句尾押韵路由能力。
原文摘要 · Abstract (English)
We study planning site formation in language models -- where internal representations of structurally-constrained future tokens form during the forward pass, and whether they causally drive generation. Using rhyming-couplet completion as a clean test of forward-looking constraint, we apply two lightweight methods (linear probing and activation patching) across Qwen3, Gemma-3, and Llama-3 at more than ten scales. Probing shows that future-rhyme information is linearly decodable at the line boundary, with signal that strengthens with scale in all three families. Activation patching reveals that only Gemma-3-27B causally relies on this encoding, exhibiting a handoff in which the causal driver migrates from the rhyme word to the line boundary around layer 30. Every other model we test conditions on the rhyme word throughout generation, with near-zero causal effect at the line boundary despite strong probe signal. We localize the Gemma-3-27B handoff to five attention heads through two-stage path patching that recover ~90% of the rhyme-routing capacity at the newline.
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。