Metraipolis › archive › dc_72900a600bea

Does the Linguistic Register of Thinking Matter? Wenyan as a Compact Reasoning Register for Chinese LLMs — arXiv:2610.19741

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.19741
License (as archived): CC0-1.0
Archived: 2026-10-15T20:02:47.221Z
SHA-256 of the archived text: 7797209fed6813301a6c8144c8636341d4dade446e8572f5f35f3773c0f9868b
Stable URL of this page: https://metraipolis.com/documento/dc_72900a600bea

How to cite

Does the Linguistic Register of Thinking Matter? Wenyan as a Compact Reasoning Register for Chinese LLMs — arXiv:2610.19741 — arXiv (en), https://arxiv.org/abs/2610.19741 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_72900a600bea (Metraipolis archive dc_72900a600bea, sha256 7797209fed6813301a6c8144c8636341d4dade446e8572f5f35f3773c0f9868b)

BibTeX

@misc{dc72900a600bea,
  title = {Does the Linguistic Register of Thinking Matter? Wenyan as a Compact Reasoning Register for Chinese LLMs — arXiv:2610.19741},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19741},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_72900a600bea; sha256 7797209fed6813301a6c8144c8636341d4dade446e8572f5f35f3773c0f9868b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19741. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.19741 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T19:35:48.368Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).