Tracing How Language Models Integrate Temporal Anchors into Factual Recall

The paper introduces anchored factual recall, where language models must choose an object for a subject–relation pair conditioned on an explicit anchor such as a time. Using causal interventions on four open‑weight models, the authors identify two parallel computational routes: a subject‑mediated route that aligns the subject representation with the queried year, and a direct route that lets the final position attend to the anchor and uses upper‑layer MLPs to bias the answer. These routes combine to determine the model’s answer, showing that factual recall involves selecting among context‑dependent alternatives rather than retrieving a single stored object.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

• llms