arXiv：cs.CL· Minghan Li, Guodong Zhou·· 7 小时前
文言作为中文 LLM 的紧凑推理语域：Wenyan Thinking 研究
Does the Linguistic Register of Thinking Matter? Wenyan as a Compact Reasoning Register for Chinese LLMs
AI 导读
研究者提出 Wenyan Thinking，将中文推理 LLM 的中间推理改写为文言文并保留简短直接答案，基于改写后的监督数据微调 Qwen3-4B-Thinking-2507。
正文
Abstract:Visible reasoning traces of Chinese reasoning-oriented LLMs are typically written in modern vernacular Chinese, which may be verbose under limited decoding budgets. We ask whether the linguistic register of reasoning can be used to improve efficiency. We propose Wenyan Thinking, which emits intermediate reasoning in Classical Chinese (wenyanwen) while retaining a short direct-answer output. Starting from modern-Chinese reasoning traces, we rewrite only the reasoning field into wenyan and fine-tune Qwen3-4B-Thinking-2507 on the rewritten supervision. To distinguish register shift from generic compression, we construct a compact modern-Chinese control using the same source data, teacher family, base model, and SFT recipe. Across budget-sensitive evaluations on MMLU-ProX-Lite-ZH, CEVAL, and AGIEval-CN, Wenyan Thinking substantially reduces reasoning length and missing-answer rates under constrained decoding. Compact rewriting explains much of the efficiency gain, while wenyan consistently outperforms the compact modern-Chinese control on the primary benchmark and remains competitive across the additional benchmarks. These results identify linguistic register as a practical design axis for efficient visible reasoning in Chinese LLMs.
| Comments: | 19 pages |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.19741 [cs.CL] |
| (or arXiv:2610.19741v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.19741 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Minghan Li [view email]
[v1]
Wed, 14 Oct 2026 08:04:05 UTC (68 KB)
来源：arXiv：cs.CL · arxiv.org