Jacobian-Causal 记忆控制（JCMC）：面向语言模型系统持久记忆的因果干预方法

View PDF HTML (experimental)

Abstract:Persistent-memory systems choose not only which records are retrieved but which prior information can alter current inference. We propose Jacobian-causal memory control (JCMC), which represents each authorized memory intervention by a predicted influence signature in a shared behavioral measurement space, selects interventions against a target effect and side-effect budget, and compares predicted with observed effects before retaining or rolling back the intervention. Under explicit smoothness and bounded-estimation assumptions, we prove a quadratic local-approximation bound, characterize the target effects reachable by a set of signatures, bound selection regret under signature error, and bound non-additive interactions between simultaneous memories. The paper reports no benchmark measurements; it defines a paired counterfactual estimator and an evaluation protocol comparing JCMC with relevance, graph, and policy-filtered retrieval baselines. The central claim is narrowed or falsified if those simpler baselines match effect targeting, side-effect control, and rollback utility under equal model, memory, policy, and cost budgets.

Comments:	Architecture and formal analysis preprint. Four conditional theorems; no benchmark measurements. Companion research essay: this https URL
Subjects:	Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)
ACM classes:	I.2.6; I.2.7; I.2.11
Cite as:	arXiv:2611.08779 [cs.AI]
	(or arXiv:2611.08779v1 [cs.AI] for this version)
	https://doi.org/10.48550/arXiv.2611.08779 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Marvin Danig [view email]
[v1] Thu, 5 Nov 2026 23:02:53 UTC (13 KB)