---
title: "基于正负例思维链的表格-文本混合金融数据自动问答方法 — 李希 2025"
description: "Answering questions over financial reports that mix tables and prose requires multi-step numerical reasoning, and LLMs still struggle with it."
authors: ["李希", "刘喜平", "舒晴", "谭钊", "万常选", "刘德喜"]
year: 2025
venue: "中文信息学报 (Journal of Chinese Information Processing)"
source: "http://jcip.cipsc.org.cn/article/id/zwxxxb_3951"
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-2025-positive-negative-chain/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/li-2025-positive-negative-chain/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2025](https://md.research.elamur.ai/free/papers/2025/page/3/) / 基于正负例思维链的表格-文本混合金融数据自动问答方法

# 基于正负例思维链的表格-文本混合金融数据自动问答方法

**Authors:** 李希, 刘喜平, 舒晴, 谭钊, 万常选, 刘德喜 · **Year:** 2025 · **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](http://jcip.cipsc.org.cn/article/id/zwxxxb_3951) · [PDF](http://jcip.cipsc.org.cn/cn/article/pdf/preview/zwxxxb_3951.pdf)

## Summary
Answering questions over financial reports that mix tables and prose requires multi-step numerical reasoning, and LLMs still struggle with it. Program-of-Thoughts (PoT) prompting, for example, reaches only 64.5% accuracy on FinQA. Its demonstrations are also hand-crafted, which is costly and hard to justify. The authors instead select demonstrations automatically, drawing on how teachers use both worked examples and typical mistakes. GPT-3.5-Turbo first answers FinQA training questions zero-shot. Correctly solved items become a positive set, and failed items become a negative set. Questions in each set are embedded with Sentence-BERT and clustered with k-means, and the centroid items form the sample pools. Every prompt then pairs a fixed best-performing positive example with two retrieved negatives that resemble the current question. The example Python code also carries line-by-line comments, which keep generated programs concise and prevent garbled variable names. Finally, the authors corrected annotation errors in FinQA, producing FinQA-fix. The method improves accuracy by 3.6% on FinQA and 12.73% on FinQA-fix. These results show that both demonstration choice and data quality strongly affect financial numerical reasoning.

## Key points
- Positive and negative pools come from LLM outputs. The number of clusters was chosen by silhouette coefficient: k=9 for positives and k=10 for negatives. Selection is static for the best positive and dynamic for the two nearest negatives.
- On FinQA (8,281 expert-written QA pairs; 6,251/883/1,147 train/dev/test), accuracy rises by 3.6% over the original PoT setup with 4 demonstrations.
- The authors estimate that nearly 20% of FinQA answers are wrong. They sort these errors into seven types, including wrong formulas, sign errors, unit mistakes, and Unicode noise. The revised FinQA-fix dataset yields a 12.73% accuracy gain.
- The method was also tested on TAT-QA with a 15-sample negative pool grouped by answer type (7 Span, 4 Multi-spans, 4 Arithmetic). It used 6 demonstrations (4 positive, 2 similar negative) against PoT's 8.
- Commented code in the prompts fixed failures such as undefined, truncated variable names, giving a small improvement over the PoT baseline.

*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{2025,
  title = {{基于正负例思维链的表格-文本混合金融数据自动问答方法}},
  author = {李希 and 刘喜平 and 舒晴 and 谭钊 and 万常选 and 刘德喜},
  journal = {中文信息学报 (Journal of Chinese Information Processing)},
  year = {2025},
  url = {http://jcip.cipsc.org.cn/article/id/zwxxxb_3951}
}
```

- [← previous 基于强化学习的古今汉语句子对齐研究](https://md.research.elamur.ai/free/papers/yu-2025-sentence-alignment-ancient/)
- [next → 基于词性对齐与依存关系的中文排比句生成方法](https://md.research.elamur.ai/free/papers/zhong-2025-chinese-parallelism-generation/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/papers/2025/page/3/)