{"ID":5439454,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-02T18:17:20.333465587Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.30788","arxiv_id":"2606.30788","title":"Revocable Learned State via Process Sidecars","abstract":"Language models are often adapted in stages: a public skill phase, a private memory phase, and a later safety phase that learns to refuse outputs tied to the remembered entities. Revoking the memory after the safety phase is not the same problem as subtracting the memory update: the later safety optimizer has transported the memory direction. We introduce process sidecars, a two-coefficient edit family $\\hatθ(λ,γ)=θ_{\\mathrm{AMS}}-λΔ_{\\mathrm{M}}-γ\\hat{R}_{\\mathrm{S}\\leftarrow\\mathrm{M}}$, with $\\hat{R}_{\\mathrm{S}\\leftarrow\\mathrm{M}}=\\hat{J}_{\\mathrm{S},\\varepsilon}(Δ_{\\mathrm{M}})-Δ_{\\mathrm{M}}$, where $\\hat{J}_{\\mathrm{S},\\varepsilon}$ is a centered secant through the realized future AdamW safety-training process. The implementation uses $\\varepsilon=1$ at the natural memory-edit scale; it reuses $θ_{\\mathrm{AMS}}$ as the positive endpoint and computes one additional safety trace at $θ_{\\mathrm{A}}-Δ_{\\mathrm{M}}$. We prove two things. First, the exact sidecar, using the true transported direction $R_{\\mathrm{S}\\leftarrow\\mathrm{M}}$ rather than the secant estimate, at $(λ,γ)=(1,1)$ recovers the counterfactual safety-only oracle $θ_{\\mathrm{AS}}$ up to second order; the proof treats AdamW as an augmented-state map over parameters, first moments, and second moments. Second, this process information is necessary: whenever future safety training bends the memory direction, every scalar task-arithmetic edit leaves first-order counterfactual error, while the process-sidecar edit is second-order accurate. Across three models, the validation-selected 2D edit improves held-out refusal closure over naive task arithmetic in all trials, and over the $γ=λ$ process-JVP subfamily, the diagonal slice of the cached 2D grid, in all paired trials.","short_abstract":"Language models are often adapted in stages: a public skill phase, a private memory phase, and a later safety phase that learns to refuse outputs tied to the remembered entities. Revoking the memory after the safety phase is not the same problem as subtracting the memory update: the later safety optimizer has transport...","url_abs":"https://arxiv.org/abs/2606.30788","url_pdf":"https://arxiv.org/pdf/2606.30788v1","authors":"[\"John Sweeney\"]","published":"2026-06-29T18:18:36Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.CL\",\"cs.CR\"]","methods":"[\"Language Model\"]","has_code":false}