---
title: "K-CoT：基于关键词思维链提示的中文排比句生成研究 — 钟茂生 2026"
description: "Chinese parallelism (排比) consists of three or more clauses with matching syntax, a shared theme and a unified emotional tone."
authors: ["钟茂生", "甘家其", "张鹤君", "谢林康", "易洁", "刘淦林"]
year: 2026
venue: "中文信息学报 (Journal of Chinese Information Processing)"
source: "http://jcip.cipsc.org.cn/article/doi/10.3969/j.issn.1003-0077.2026.07.014"
doi: "10.3969/j.issn.1003-0077.2026.07.014"
licence: "Free access (jcip.cipsc.org.cn), no open licence stated — readonly; © 中文信息学报"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/papers/zhong-2026-k-cot-chinese/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/zhong-2026-k-cot-chinese/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2026](https://md.research.elamur.ai/free/papers/2026/page/3/) / K-CoT：基于关键词思维链提示的中文排比句生成研究

# K-CoT：基于关键词思维链提示的中文排比句生成研究

**Authors:** 钟茂生, 甘家其, 张鹤君, 谢林康, 易洁, 刘淦林 · **Year:** 2026 · **Venue:** 中文信息学报 (Journal of Chinese Information Processing) · **Licence:** Free access (jcip.cipsc.org.cn), no open licence stated — readonly; © 中文信息学报

**Links:** [Publisher's page](https://doi.org/10.3969/j.issn.1003-0077.2026.07.014) · [PDF](http://jcip.cipsc.org.cn/cn/article/pdf/preview/10.3969/j.issn.1003-0077.2026.07.014.pdf) · [DOI 10.3969/j.issn.1003-0077.2026.07.014](https://doi.org/10.3969/j.issn.1003-0077.2026.07.014)

## Summary
Chinese parallelism (排比) consists of three or more clauses with matching syntax, a shared theme and a unified emotional tone. Research on generating it has been held back by two gaps: little high-quality data and no fine-grained annotation. LLMs also tend to produce clauses that are structurally misaligned or that drift off-topic. The authors address the data gap with CPDAK, a corpus drawn from prose, fiction, essays and student compositions. Each parallel sentence is annotated with its topic, parallel marker words, tone and keywords.

On top of this corpus they propose K-CoT, a prompting framework that needs no fine-tuning. It works in three steps:
- It selects diverse few-shot demonstrations through clustering.
- It derives keywords from the topic and tone through a step-by-step reasoning chain, with a semantic-similarity check.
- It produces the parallel sentence, then has the model reflect on its draft and revise it.

Across five open 6–9B LLMs, K-CoT beats plain prompting, standard CoT and a fine-tuned baseline. This points to keyword-mediated reasoning as an interpretable way to steer rhetorical generation.

## Key points
- **CPDAK corpus:** about 10,023 sentences, 6,529 annotated parallelism instances and roughly 433K tokens. Each instance is labelled with a (Topic, Flag, Tone, Keywords) tuple. Inter-annotator agreement was measured with three annotators on 500 samples and reached Fleiss' Kappa = 0.78. The corpus is released on GitHub.
- **Candidate filtering:** candidates were pre-filtered by a Text2Vec-based RoBERTa Large classifier with a confidence threshold of 0.673. The classifier was trained on a balanced set of 5,195 examples, with couplets, repetition sentences and ordinary sentences serving as negatives.
- **K-CoT demonstration selection:** a dual-channel clustering combines BERT [CLS] embeddings with keyword embeddings (k=20 each, silhouette score > 0.6). Five demonstrations are drawn from it.
- **K-CoT keyword filtering:** generated keywords are kept only if their Sentence-BERT similarity to the topic exceeds 0.75.
- **Models tested:** ChatGLM3-6B, Baichuan2-7B, Qwen-2.5-7B, Yi-1.5-9B and LlaMA3-8B-Chinese-Chat.
- **Baselines:** CPGen-POS&DEP (fine-tuned), Vanilla prompting, and CoT with randomly chosen demonstrations.
- **Evaluation:** automatic metrics were BLEU and Distinct. Human raters scored five dimensions (structure, fluency, emotion, creativity, vividness) on a 1–3 scale.
- **Headline result:** with Qwen, K-CoT reached a BLEU-4 of 66.37, about a 107% gain over CPGen-POS&DEP, and improved the other metrics as well.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/shelves/linguistics/) · [Natural language processing](https://md.research.elamur.ai/free/shelves/nlp/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@article{2026k,
  title = {{K-CoT：基于关键词思维链提示的中文排比句生成研究}},
  author = {钟茂生 and 甘家其 and 张鹤君 and 谢林康 and 易洁 and 刘淦林},
  journal = {中文信息学报 (Journal of Chinese Information Processing)},
  year = {2026},
  doi = {10.3969/j.issn.1003-0077.2026.07.014},
  url = {https://doi.org/10.3969/j.issn.1003-0077.2026.07.014}
}
```

- [← previous JudgeMeNot: Personalizing Large Language Models to Emulate Judicial Reasoning in Hebrew](https://md.research.elamur.ai/free/papers/findings-2026-razumenko-judgemenot-personalizing-large-language-models/)
- [next → KCIF: Knowledge-Conditioned Instruction Following](https://md.research.elamur.ai/free/papers/murthy-2026-kcif-knowledge-conditioned-instruction-following/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/papers/2026/page/3/)