Large language models can interpret natural language, yet robust decisions remain challenging.
Jev-like models expose structured choices, but these interfaces do not directly provide numerical values at a requested precision.
We propose NUMERICJEV, a training-free numerical decoding algorithm that enables numerical output from any LLM with a Jev-like structured-choice interface.
Surprisingly, on our arithmetic benchmark, it outperforms direct selection from a candidate 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 recursively refines a range through a multiway decision 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 direct choice.
A separate three-date historical-index study yields 4.58% mean relative recall error and 0% readout error when the value is supplied.
Code is available at https://github.com/Bring-AI/jev-numeric.