研究大模型循环中如何用少量文本有效引导并持久改变输出方向。
Perturbation Dose Responses in Recursive LLM Loops: Raw Switching, Stochastic Floors, and Persistent Escape under Append, Replace, and Dialog Updates
- 分离模型与上下文更新规则，对比追加、替换、对话三种方式的引导效果。
- 追加模式下持久引导成功率最高仅36%，满历史时达75%-80%且可稳定维持。
- 发现看似稳定的引导差异实为短期终点定义偏差，非深层结构问题。
递归语言模型循环常陷入特定吸引子模式。核心问题是：注入多少文本才能将其引导至新状态，且该变化是否持久？本文在30步递归循环中，将模型与上下文更新规则解耦，分别测试追加、替换和对话更新策略。结果表明，在12,000字符尾部剪裁条件下，目标一致性持久性峰值约16%，源基域逃逸率约36%，均未超50%；而在完整历史协议下，源基域逃逸率在400词时突破50%，1,500词时饱和于75%-80%之间（95%置信区间[0.41, 0.61]）。通过四步验证实验（异质性控制、粒度扫描、转移熵诊断、长程轨迹延续），发现高剂量下的目标一致性下降实为有限视野与终点定义敏感所致，而非结构性不对称。半数效应源于终点时机，残差从第29步的-0.143降至第79步的-0.039（置信区间跨零）。替换模式下原始切换近饱和，但主要反映状态重置覆盖；插入探针使其降至12%-32%。建议递归评估应区分瞬时移动与真实逃逸，扣除随机底噪，并视上下文更新规则为关键安全设计选择。
原文摘要 · Abstract (English)
Recursive language-model loops often settle into recognizable attractor-like patterns. The practical question is how much injected text is needed to move a settled loop somewhere else, and whether that move lasts. We study this in 30-step recursive loops by separating the model from the context-update rule: append, replace, and dialog updates expose different histories to the same generator. The main result is that persistent redirection in append-mode recursive loops is memory-policy-conditioned. Under a 12,000-character tail clip, destination-coherent persistence plateaus near 16 percent and retained source-basin escape near 36 percent at dose 400; neither crosses 50 percent. Under a full-history protocol, retained source-basin escape crosses 50 percent near 400 tokens and saturates at 75-80 percent by 1,500 tokens; destination-coherent persistence first reaches 0.50 near 1,500 tokens (Wilson 95 percent CI [0.41, 0.61]). A four-step falsification battery (heterogeneity control, granularity sweep with hierarchical macro-merge, transition-entropy diagnostic, and long-horizon trajectory continuation) recasts the high-dose destination-coherent dip as a finite-horizon, endpoint-definition-sensitive feature rather than a stable structural asymmetry. Half the canonical magnitude is endpoint timing; the residual drops 73 percent from -0.143 at step 29 to -0.039 at step 79 under the frozen canonical cluster basis, bootstrap interval straddling zero. Replace-mode raw switching is near-saturated under the default protocol but largely reflects state-reset overwrite: insert-mode probes drop it to 12-32 percent. We report 37 experiments on gpt-4o-mini with within-vendor replication on gpt-4.1-nano. Recursive-loop evaluations should distinguish transient movement from durable escape, subtract stochastic floors, and treat context-update rules as safety-relevant design choices.
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。