递归预测的偏差源于自生成状态下的认知不确定性，而非单纯分布偏移。
Exposure Bias as Epistemic Underidentification in Recursive Forecasting
- 引入诱导状态与溯源变量，揭示递归预测中的认知不完整问题
- 实证发现滚动预测进入独立的诱导状态区间，局部修正任务不同
- 溯源感知的修正可提升性能，但效果依赖具体场景
递归多步预测通常被理解为分布偏移：模型在观测历史上训练，却部署于自身预测。我们证明这一视角不完整——在部分可观测或状态截断下，递归滚动也是认知不完整问题。即使潜在动力学确定，单步贝叶斯监督仅在可观测上下文中识别行为，无法确保在滚动生成的自诱导状态中正确识别部署的预测器，因其局部目标不能仅由数值状态决定。我们形式化引入诱导状态 $Z$ 与溯源变量 $P$，并推导出诱导状态误差的分解：教师强制/滚动不匹配、表示-类别近似误差、溯源信息缺口。实证表明，滚动进入独立的诱导状态区间，固定诱导状态定义了独立的局部校正任务，闭环收益不仅来自局部适应，还来自滚动过程中访问的诱导状态变化。使用简单的二元溯源编码，溯源感知校正可进一步提升性能，但增益是条件性的而非普遍的。这些结果将暴露偏差重新解释为在自诱导认知不确定性下的推理。
原文摘要 · Abstract (English)
Recursive multi-step forecasting is usually framed as distribution shift: models are trained on observed histories but deployed on their own predictions. We show this framing is incomplete by proving that, under partial observability or state truncation, recursive rollout is also an epistemic underidentification problem. Even with deterministic latent dynamics, one-step Bayes supervision identifies behavior only on observed contexts and need not identify the deployed recursive predictor once rollout queries self-generated induced states whose correct local targets are not determined by numeric state alone. We formalize this with induced states $Z$ and provenance variables $P$, and derive a decomposition of induced-state error into teacher-forcing/rollout mismatch, representation--class approximation, and provenance information gaps. Empirically, we show that rollout enters a distinct induced-state regime, that fixed induced states define a distinct local corrective task, and that closed-loop gains arise not only from local adaptation but also from changing the induced states visited during rollout. Using a simple binary provenance encoding, provenance-aware correction can further improve performance, though gains are conditional rather than uniform. These results recast exposure bias as reasoning under self-induced epistemic uncertainty.
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。