arXiv 论文：可解释性工具可跨模型复用，覆盖 110 组模型对验证
Interpretability Is Not Model-Specific
做模型可解释性的人值得看这篇：以前每个模型都要重新拟合拒绝方向和探针，现在证明换个模型也能直接用，加少量无标签 prompt 就能接近原生效果。覆盖五个模型家族、1B 到 72B，实验量够扎实。
一篇 arXiv 论文（2611.12675）研究了可解释性工具能否跨模型迁移。作者把拒绝方向、正确性方向、情感探针三类工具，在来自五个家族、参数量 1B 到 72B 的 110 组模型对之间迁移，同时覆盖 base 与 instruction-tuned 模型，并用五组随机种子做对照实验。
迁移效果取决于对齐映射所用的数据。仅在普通问题上拟合的无标签映射，能恢复目标模型自身拒绝调控效果的 54%，恢复正确性提升的 16% 到 77%；加入工具作用区域的无标签提示词后，两项指标分别提升到 102% 和 88% 到 98%，而对照方向的恢复率不超过 1%。论文还证明当两个模型在映射覆盖的数据上线性对应时，线性映射就会表现出这种特性，并据此提出一个无需标签的覆盖率评分，在超过 16,000 次运行中追踪恢复效果。
这项工作意味着可解释性结果一经发现即可跨模型复用，成本仅为少量无标签提示词，解释了此前跨域迁移失败的报告，也降低了对每个模型单独做可解释性分析的成本。
Interpretability Is Not Model-Specific
Interpretability tools are usually built for one model at a time: a refusal direction, a truthfulness probe, or a steering vector is found with labeled data inside the model it explains. We ask whether such tools can be carried to other models through a map between residual streams fit only on unlabeled prompts. We transfer a refusal direction, tested causally by addition and ablation, and two read-out tools, a correctness direction and a sentiment probe, across 110 pairs of models from five families and 1B to 72B parameters and between base and instruction-tuned models, with controls for specificity and five seeds. How much transfers depends on what the map was fit on. A map fit on ordinary questions recovers 54\% of the target's own refusal steering and 16\% to 77\% of its correctness gain; adding unlabeled prompts from the region where the tool operates raises these to 102\% and 88\% to 98\%, while control directions recover at most 1\%. We prove that a linear map behaves this way whenever two models correspond linearly on the data it covers, and a label-free coverage score derived from this result tracks recovery across more than 16,000 runs and explains earlier reports that maps between models fail across domains. Carried read-out tools outperform anything the target's unlabeled representations yield. Interpretability results, once found, can be reused across models at the cost of a few unlabeled prompts.
本条情报归属 AITOP「论文」核心栏目，重点聚焦北美前沿实验室与硅谷科技巨头。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：可解释性、arXiv、steering vector、迁移学习，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明：本文原始线索采编自「arXiv cs.AI」（@Marcus Armstrong, Navid Ayoobi, Pradham Mummaleti, Alexander Chulzhanov, Arjun Mukherjee），经 AITOP 多维评分管线结构化提炼。
