---
title: "基于检索增强思维提示的汉语框架语义解析方法 — 李迎旭 2026"
description: "The paper addresses Chinese Frame Semantic Parsing (CFSP): choosing the semantic frame evoked by a target word, locating its arguments, and labeling…"
authors: ["李迎旭", "陈涛", "李斌阳", "黎议泽"]
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.1003-0077.2026.06.001"
doi: "10.3969/j.issn.1003-0077.2026.06.001"
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/li-2026-retrieval-augmented-chain/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/li-2026-retrieval-augmented-chain/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2026](https://md.research.elamur.ai/free/papers/2026/page/5/) / 基于检索增强思维提示的汉语框架语义解析方法

# 基于检索增强思维提示的汉语框架语义解析方法

**Authors:** 李迎旭, 陈涛, 李斌阳, 黎议泽 · **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.1003-0077.2026.06.001) · [PDF](http://jcip.cipsc.org.cn/cn/article/pdf/preview/10.3969/j.issn.1003-0077.2026.06.001.pdf) · [DOI 10.3969/j.issn.1003-0077.2026.06.001](https://doi.org/10.3969/j.issn.1003-0077.2026.06.001)

## Summary
The paper addresses Chinese Frame Semantic Parsing (CFSP): choosing the semantic frame evoked by a target word, locating its arguments, and labeling their roles. Existing LLM prompting approaches use shallow reasoning chains and make little use of retrieval, so they perform poorly. The authors, from the University of International Relations in Beijing, propose a modular, fine-tuning-free prompting pipeline that combines retrieval-augmented generation (RAG) with chain-of-thought (CoT) reasoning. Each stage feeds the next.

- **Frame identification:** prompts add plain-language explanations of key concepts and a guided reasoning path. Retrieved similar examples serve as few-shots, and the frames found in those examples form a restricted candidate set.
- **Argument identification:** recast as generation that wraps arguments in [start]/[end] markers.
- **Role identification:** recast as N-way classification over the roles of the chosen frame.

On CFN 2.1, the method outperforms a ChatGPT+CoT baseline and the PKU sparse-retrieval system across three LLMs. This shows that careful prompt design can substantially narrow the gap with fine-tuned systems.

## Key points
- Evaluation uses CFN 2.1, with 80% held out as a retrieval knowledge base and 20% used for testing. The tested models are GPT-3.5-turbo, Qwen1.5-32B and DeepSeek-R1-distill-Qwen-32B.
- On Qwen1.5-32B, the method beats PKU by 13.52 points in frame accuracy (67.47%), 2.24 in argument F1 (53.26%) and 5.09 in role F1 (18.62%).
- Dense retrieval works better than sparse retrieval. BGE-M3 with 10 shots, CoT and candidate frames reaches 67.43% frame accuracy, compared with 63.95% for BM25. Going to 20 shots adds only about 0.04.
- In ablations, role labeling depends heavily on frame results. Passing frame results into argument identification, however, lowered argument F1 from 53.26 to 46.30 because errors accumulated.
- Role identification remains weak overall: the best F1 is 26.46%, achieved by DeepSeek-R1-distill-Qwen-32B.

*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{2026,
  title = {{基于检索增强思维提示的汉语框架语义解析方法}},
  author = {李迎旭 and 陈涛 and 李斌阳 and 黎议泽},
  journal = {中文信息学报 (Journal of Chinese Information Processing)},
  year = {2026},
  doi = {10.3969/j.issn.1003-0077.2026.06.001},
  url = {https://doi.org/10.3969/j.issn.1003-0077.2026.06.001}
}
```

- [← previous 基于事实验证的五链式机器翻译幻觉检测智能体](https://md.research.elamur.ai/free/papers/wei-2026-fact-verification-five/)
- [next → 基于解耦与组合的大模型知识问答方法](https://md.research.elamur.ai/free/papers/shi-2026-leveraging-decoupled-composition/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/papers/2026/page/5/)