用向量符号架构设计安全合约,防大模型上下文漂移
Holographic Invariant Storage: Design-Time Safety Contracts via Vector Symbolic Architectures
- 利用双极向量符号架构构建设计期安全协议
- 保证信号恢复保真度达0.707,抗噪能力随噪声强度提升
- 适用于大模型系统设计阶段的安全预算与容量规划
我们提出全息不变存储(Holographic Invariant Storage, HIS),将双极向量符号架构的已知特性整合为大语言模型上下文漂移缓解的设计期安全合约。该合约在部署前即可评估三项闭式保证:单信号恢复保真度收敛至约0.707(与噪声深度或内容无关),连续噪声鲁棒性为2Φ(1/σ)−1,多信号容量退化约为√(1/(K+1))。这些边界经蒙特卡洛模拟(n = 1,000)验证,使系统工程师可在设计阶段预估恢复保真度与码本容量——这是时序或嵌入距离指标无法提供的能力。一次试点行为实验(4个大模型,2B–7B参数,720次试验)证实,在2B规模下安全重注入可提升行为一致性;完整结果见附录。
原文摘要 · Abstract (English)
We introduce Holographic Invariant Storage (HIS), a protocol that assembles known properties of bipolar Vector Symbolic Architectures into a design-time safety contract for LLM context-drift mitigation. The contract provides three closed-form guarantees evaluable before deployment: single-signal recovery fidelity converging to $1/\sqrt{2} \approx 0.707$ (regardless of noise depth or content), continuous-noise robustness $2Φ(1/σ) - 1$, and multi-signal capacity degradation $\approx\sqrt{1/(K+1)}$. These bounds, validated by Monte Carlo simulation ($n = 1{,}000$), enable a systems engineer to budget recovery fidelity and codebook capacity at design time -- a property no timer or embedding-distance metric provides. A pilot behavioral experiment (four LLMs, 2B--7B, 720 trials) confirms that safety re-injection improves adherence at the 2B scale; full results are in an appendix.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。