高风险领域AI需主动放弃能力以求可靠，复杂模型反而易出错。
Epistemic Compression: The Case for Deliberate Ignorance in High-Stakes AI
- 通过架构设计强制简化模型，避免过度拟合不可靠数据。
- 在15个高风险领域中，86.7%的案例验证了该方法优于复杂模型。
- 适合医疗、金融等规则变化快、数据少的场景使用。
基础模型在稳定环境中表现优异，但在医疗、金融、政策等对可靠性要求高的领域常失效。这种‘可信度悖论’不仅是数据问题，更是结构性问题：在规则随时间变化的领域，增加模型容量会放大噪声而非捕捉信号。本文提出‘认知压缩’原则——鲁棒性源于将模型复杂度匹配数据的可变周期，而非盲目扩大参数量。不同于传统正则化事后惩罚权重，认知压缩通过架构设计实现简约：模型结构本身使表达超出证据的数据方差变得代价高昂。我们引入‘制度指数’，区分‘变动制度’（不稳定、数据少；宜简单）与‘稳定制度’（恒定、数据多；可复杂）。在15个高风险领域的探索性综合分析中，该指数与实证最优建模策略一致率达86.7%（13/15）。高风险AI应从盲目扩展转向有原则的简洁性。
原文摘要 · Abstract (English)
Foundation models excel in stable environments, yet often fail where reliability matters most: medicine, finance, and policy. This Fidelity Paradox is not just a data problem; it is structural. In domains where rules change over time, extra model capacity amplifies noise rather than capturing signal. We introduce Epistemic Compression: the principle that robustness emerges from matching model complexity to the shelf life of the data, not from scaling parameters. Unlike classical regularization, which penalizes weights post hoc, Epistemic Compression enforces parsimony through architecture: the model structure itself is designed to reduce overfitting by making it architecturally costly to represent variance that exceeds the evidence in the data. We operationalize this with a Regime Index that separates Shifting Regime (unstable, data-poor; simplicity wins) from Stable Regime (invariant, data-rich; complexity viable). In an exploratory synthesis of 15 high-stakes domains, this index was concordant with the empirically superior modeling strategy in 86.7% of cases (13/15). High-stakes AI demands a shift from scaling for its own sake to principled parsimony.
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。