NumericJev：基于多路决策树的Jev类LLM数值解码

中文摘要 AI 辅助

大型语言模型能够解释自然语言，但稳健的决策仍然具有挑战性。Jev类模型暴露了结构化选择，但这些接口并不直接以所请求的精度提供数值。我们提出了NUMERICJEV，一种无需训练的数值解码算法，它使任何具有Jev类结构化选择接口的LLM都能产生数值输出。令人惊讶的是，在我们的算术基准测试中，它比从包含正确答案的候选列表中直接选择高出2.93个百分点（图1）。我们的动机来自观察：数值范围选择本身就是一个Jev类LLM可以解决的决策问题。NUMERICJEV通过多路决策树递归地细化范围，同时将原始问题保留在上下文中，无需参数更新或隐藏状态访问。在100个值的网格上，十路树仅需两轮决策。范围归一化MAE为1.84%，而直接选择为5.18%。一项单独的三个日期历史指数研究在提供数值时产生4.58%的平均相对召回误差和0%的读出误差。代码可在https://github.com/Bring-AI/jev-numeric获取。

英文摘要

Large language models can interpret natural lan- guage, yet robust decisions remain challenging. Jev-like models expose structured choices, but these interfaces do not directly provide numeri- cal values at a requested precision. We propose NUMERICJEV, a training-free numerical decod- ing algorithm that enables numerical output from any LLM with a Jev-like structured-choice in- terface. Surprisingly, on our arithmetic bench- mark, it outperforms direct selection from a can- didate list containing the correct answer by 2.93 percentage points (Figure 1). Our motivation comes from the observation that numerical range selection is itself a decision problem that Jev- like LLMs can address. NUMERICJEV recur- sively refines a range through a multiway deci- sion tree while retaining the original question in context, without parameter updates or hidden- state access. On a 100-value grid, a ten-way tree requires only two decision rounds. Range- normalized MAE is 1.84% versus 5.18% for di- rect choice. A separate three-date historical- index study yields 4.58% mean relative recall er- ror and 0% readout error when the value is sup- plied. Code is available at https://github. com/Bring-AI/jev-numeric.

发表机构

• The University of Tokyo（东京大学）

机构由 AI 辅助整理，请以论文原文为准。