KVEraser: Learning to Steer KV Cache for Efficient Localized Context Erasing
Post-hoc context erasing over the KV cache is challenging because a local edit has a global consequence: once a span has been processed, its influence propagates into the cached states of all subsequent tokens. This issue arises naturally in long-context LLM applications, where stale, incorrect, or harmful context may be identified only after prefill. Exact erasing must then recompute all tokens after the deleted span, making its computational cost depend on suffix length rather than erased-span length. We introduce KVEraser, a learned KV-cache editing method for efficient localized context erasing. KVEraser replaces the KV states of the erased interval with learned steering states while ...
| Authors | Mufei Li, Shikun Liu, Dongqi Fu et al. |
|---|---|
| Primary category | cs.CL |
| Published | 15 June 2026 |
| Last updated at source | 29 September 2026 |
Connected in the knowledge graph
- Graph-COM/KVEraserDataset · cited by
Models and datasets referencing this paper
- Graph-COM/KVEraserDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.