Chinese Decision：面向单次前向概率决策的中文语言模型家族

Authors:Qiang Yan (Institute of Computing Technology, Chinese Academy of Sciences)

Abstract:Many language-based applications require probabilities over a finite set of decisions rather than open-ended responses. We present Chinese Decision, a family of Chinese-language models for single-pass probabilistic decision-making. Given context, an instruction, and candidate descriptions, the model extracts final-position candidate-letter logits in one forward pass and normalizes them over valid options, without autoregressive answer generation. A shared interface supports Boolean judgments, categorical choices, and ordinal scores. We report a completed 0.8B model trained with distribution cross-entropy on 13.048 million decisions and preliminary 2B checkpoints trained with an additional RLCD objective. On the full CJ-Bench of 307,900 decisions, the uncalibrated 0.8B model achieves 72.24% general-domain accuracy and 76.98% average accuracy across medicine, law, and finance using a single checkpoint, with 1.07% overall expected calibration error. The 2B model reaches 72.56% general-domain accuracy after 40.13% of one epoch but has not surpassed the completed 0.8B model on the professional-domain average. We further evaluate a validation-temperature-scaled deployment model and its Q8 quantization, finding close aggregate performance while documenting individual prediction changes. We release the training, evaluation, and deployment pipeline. The current results establish a reproducible approach to Chinese probabilistic decisions but do not isolate the effect of model scale.

Comments:	11 pages, 2 figures, 11 tables. Code: this https URL
Subjects:	Computation and Language (cs.CL)
Cite as:	arXiv:2610.23170 [cs.CL]
	(or arXiv:2610.23170v1 [cs.CL] for this version)
	https://doi.org/10.48550/arXiv.2610.23170 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Qiang Yan [view email]
[v1] Fri, 16 Oct 2026 09:08:32 UTC (80 KB)