We document inverse scaling in LLMs on forecasting problems whose underlying time series exhibit superlinear growth and tail risk of regime change, a structure common in finance and epidemiology. On these tasks, more capable models produce worse distributional forecasts. The pattern appears on ForecastBench-Sim (FBSim), a contamination-free, simulated-world benchmark we release, in forecasting synthetic SIR epidemics with a matched linear control, and replicates in real-world datasets on COVID-19, measles, housing markets, and hyperinflation. A per-quantile decomposition shows the failure concentrates at the upper tail, which more capable models shift upward to track aggressive extrapolations of growth, while the lower tail stays put. A within-family study of Llama-3.1 shows that both model scale and post-training independently contribute to this effect. Domain knowledge does not reliably rescue calibration. This inverse scaling does not appear on single-threshold metrics common in LLM forecasting benchmarks, reversing the sign of the capability--accuracy relationship on identical outputs. Single-threshold scoring at conventional cutoffs misses the upper-tail cost; tail-inclusive scoring reverses the sign of the capability--accuracy relationship on the same outputs. We recommend that LLM forecasting evaluations use continuous (and unbounded) measures of accuracy alongside bounded binary threshold metrics.

翻译：我们在大语言模型（LLM）中发现了预测问题的逆缩放现象，其底层时间序列呈现出超线性增长和体制转变的尾部风险，这种结构常见于金融和流行病学领域。在这些任务中，能力更强的模型会产生更差的分位分布预测。该模式出现在我们发布的零污染模拟基准FBSim（ForecastBench-Sim）上，在预测具有匹配线性对照的合成SIR疫情时表现明显，并在COVID-19、麻疹、住房市场和恶性通货膨胀等真实世界数据集中得到复现。通过分位数分解可知，失败集中于上尾部分——更强大的模型通过向上调整尾部以追踪激进的增长外推，而下尾保持稳定。对Llama-3.1的族内研究表明，模型规模和后训练均独立导致了该效应。领域知识无法可靠地改善校准效果。这种逆缩放现象在LLM预测基准常见的单阈值指标上并未出现，反而在相同输出上逆转了能力-准确率关系的符号。传统截断点的单阈值评分掩盖了上尾代价；而包含尾部的评分则能在相同输出上反转能力-准确率关系的符号。我们建议LLM预测评估应使用连续（且无界）的准确率度量，同时辅以有界二进制阈值指标。