早期編碼，晚期使用：Transformer 從何處開始依據推斷出的夥伴專長採取行動

摘要

Transformer 模型可以在其殘差流中，於某個深度使某項屬性可被線性解碼，而在該深度這項屬性尚未影響輸出。這種資訊可被讀取的位置與其被使用的位置之間的落差，已在直接陳述於輸入中的屬性上獲得證實。我們探問此落差是否也適用於模型必須在對話中逐步推論的屬性，也就是其對話夥伴有多專業。我們使用 ExpertCollab——一個由模型扮演四種專業程度角色之間多輪研究規劃對話所構成的語料庫——發現夥伴專業程度在早期層最容易解碼，並在網路中點之前降至接近隨機水準。反事實修補顯示，在可解碼性高峰層注入專業程度差異，幾乎不改變固定的後層讀出；然而，同樣的差異若在中點之後注入，則幾乎完全傳播，兩者差距超過一個數量級。內容匹配的隨機對照與無探針診斷將此轉折定位在同一早期層，而一個靜態指定的控制屬性則全程保持可解碼。因此，一項被推論出的關係屬性會在其開始具因果作用之前許久便已被表徵，這界定了任何試圖讀出或引導以夥伴為條件之行為的介入必須落在何處。我們僅以單一模型在合成語料庫上作為初步展示。

English

A transformer can make an attribute linearly decodable in its residual stream at a depth where that attribute does not yet influence the output. This gap between where information is readable and where it is used has been shown for attributes stated directly in the input. We ask whether it also holds for an attribute the model must infer gradually over a conversation, namely how expert its dialogue partner is. Using ExpertCollab, a corpus of multi-turn research-planning dialogues between model-played personas at four expertise levels, we find that partner expertise is most decodable in the early layers and falls to near chance before the midpoint of the network. Counterfactual patching shows that injecting the expertise difference at the layer of peak decodability barely changes a fixed late-layer readout, whereas the same difference injected past the midpoint propagates almost completely, a separation of more than an order of magnitude. A content-matched random control and a probe-free diagnostic place the transition at the same early layer, and a statically specified control attribute stays decodable throughout. An inferred relational attribute is therefore represented well before it becomes causally active, which bounds where any attempt to read out or steer partner-conditioned behavior must intervene. We use one model on a synthetic corpus as an initial demonstration.