infrastructure
A Contiguous Window Repaired the Stale Cache
Edit-local recomputation recovered at least 0.94 of the post-edit answer margin and ran 13–21× faster than a full prefill.
Summary
Edit-local recomputation recovered at least 0.94 of the post-edit answer margin and ran 13–21× faster than a full prefill.
Editing a retrieved document can invalidate downstream key-value states even when the change is local. Across three model families and a factual retrieval benchmark, a contiguous window around the edit recovered at least 0.94 of the post-edit answer margin at the primary budget. Attention, KV-deviation and structural selectors did worse because scattered positions inherited surrounding staleness during real recomputation. Repair ran 13–21 times faster than full re-prefill. The advantage largely disappeared when answer-bearing text moved farther downstream, defining a practical boundary for the method.
Why it matters
Edit-local recomputation recovered at least 0.94 of the post-edit answer margin and ran 13–21× faster than a full prefill.
Limits and context
No additional limitation was separately recorded.
Key claims
Edit-local recomputation recovered at least 0.94 of the post-edit answer margin and ran 13–21× faster than a full prefill.
Evidence: source-2026-09-17-005
Sources
- arXiv preprint 2609.17983arXiv · primary research
Corrections
No corrections have been recorded for this story.