arXiv cs.AI· Tong Che, Yilong Li·· 10 天前AI 评分22
LLM 内部特征被模型真正使用了吗？区分引导与机制
Does the Model Use the Feature? Separating Steering from Mechanism in LLMs
AI 导读
研究提出一套实证契约，在自然输入观测值上评估特征，通过安装、移除与下游救援测试区分特征是否被模型真正使用。对三类表征的测试显示，已发表的未知实体 latent 虽能强烈引导知识弃答，但将观测值安装到匹配提示中仅能迁移自然已知—未知弃答对比的一小部分。Gemma 与 Llama 的稠密已知—未知方向在安装与移除间呈现相反不对称性，主语—动词一致性特征集能否复现行为取决于其值写入模型的方式。
正文 · 原文
Abstract:Internal features in LLMs are often interpreted as mechanisms when they track a concept and their manipulation changes a related behavior. Yet steering can push a feature far outside its natural range, where its effects need not reflect the model's own computation. We examine this inference and propose an empirical contract whose tests evaluate features at values observed on natural inputs. One test copies a feature's value from an input that shows a behavior into a matched input that does not (installation) or the reverse (removal); the other restores the feature after an upstream edit (downstream rescue). Installation measures how far the feature suffices for the behavior; removal and downstream rescue measure how much the model uses it. Applied to three kinds of representations, the two strengths separate sharply. The published unknown-entity latent strongly steers knowledge abstention, yet installing observed values from either published latent into matched prompts transfers only a small fraction of the natural known--unknown abstention contrast. Dense known--unknown directions show opposite asymmetries between installation and removal in Gemma and Llama, and how fully a released subject--verb agreement feature set reproduces and restores the behavior depends on how its values are written into the model. Tracking a concept and steering a behavior therefore do not by themselves show that the model uses a feature, and each conclusion holds only for the intervention tested.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.07270 [cs.AI] |
| (or arXiv:2610.07270v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07270 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yilong Li [view email]
[v1]
Mon, 5 Oct 2026 19:11:42 UTC (122 KB)
来源：arXiv cs.AI · arxiv.org