Jev Lora

JevSoup is a training-free framework that separates System One expert routing from System Two execution: Jev picks two LoRA experts through structured probabilities and their updates are merged with orthogonal projection. Across 14 PorTAL tasks it gains up to 1.19% task-macro accuracy over external baselines.

Open recipe for a local Jev-style decision model: a Qwen3.5-9B LoRA that scores one allowed answer token per Choice, boolean or rubric Score question, with data pipeline, training config and eval harness. Reports 90.1% on its 324-example holdout against Jev's 93.2%.

Open recipe for calibrated decision models: an LLM teacher writes training data from a one-sentence task description, a LoRA plus decision head on Qwen3-4B-Base answers Choice, Score and Noul questions with calibrated probabilities, evaluated next to Jev on identical items.