Subtract or Replay? Exact Deletion from Language-Model Memory

תקציר מקורי באנגליתarXiv:2607.27539v1 Announce Type: new Abstract: Exact deletion from persistent language-model memory depends on how that memory represents a record. Addressable influence can be removed by algebraic decrement; influence transformed by later writes inside shared recurrent state requires rebuilding from before the write. We test this distinction in two pretrained models against explicit record-omitted references. First, we replace Gemma 3's global-attention layers with support-vector memory. After low-rank recovery at 1B, decrement and retained-key refit agree at the next-token output to median KL $5.4\times10^{-15}$ over 31 support-token deletions, with $+2.0\%$ perplexity relative to a matched fine-tune. A masked-refit proxy is indistinguishable from the never-ingested floor under elicitat