Search papers, labs, and topics across Lattice.
To replace high-latency generative LLMs on structured Chinese decision-making tasks, Chinese-Jev adapts lightweight encoder-only "System One" architectures using a unified probability-target formulation trained across 10 million examples. This addresses the severe performance gap and domain degradation (in medicine, law, and finance) found in existing non-autoregressive decision models outside of English. The resulting model outperforms the closed-source Jev baseline by 1.24% on general benchmarks and 4.0% in medicine while delivering a 17x–20x speedup down to 15 ms latencies.
Non-generative "System One" models can beat closed-source baselines in Chinese decision tasks with a 20x speedup and 15 ms latency, proving encoder-only architectures remain radically underutilized for structured reasoning.
System One models such as Jev offer an efficient alternative to generative language models for tasks that require decisions rather than open-ended responses. However, existing Jev models exhibit limited Chinese-language decision accuracy, restricting their utility in both general and specialized settings. In this paper, we introduce Chinese-Jev, a System One model that addresses this gap through a unified data processing and training pipeline. Our data processing protocol converts heterogeneous Chinese-language annotations into probability targets over candidate options, enabling a shared training formulation across domains and question formats. To enable efficient inference, Chinese-Jev adopts a lightweight encoder-only backbone for text encoding and learns to score candidate answers through decision-oriented training. To address the misalignment between the pre-training distribution and downstream Chinese-language scenarios, we first train the model on a general-purpose corpus of 10 million examples, then fine-tune it separately for the medical, legal, and financial domains. To evaluate decision accuracy and calibration in both general and domain-specific Chinese-language settings, we introduce Chinese-Jev Bench (CJ-Bench). After first-stage pre-training, Chinese-Jev exceeds the accuracy of the closed-source Jev model by 1.24% on general-domain tasks while achieving a 20.3x speedup. Subsequent domain-specific fine-tuning yields a 4.0% accuracy improvement over Jev in medicine and achieves 92% of Jev's average accuracy across specialized domains, with a 17x speedup and an average latency of only 15 ms per example. We further demonstrate on-device deployment of an INT8-quantized model on mobile devices, achieving an inference latency of approximately 1.0 second per decision. The project is available at https://gulucaptain.github.io/Chinese-Jev/.
