Multi-perspective prompt fusion for zero-shot classification of agricultural news texts with large language models
Qiaoyun Liu, Yaoyao Ding, Hongyan Liu, Zeling Xu, Yuntao Zou · 2026
Read Multi-perspective prompt fusion for zero-shot classification of agricultural news texts with large language models by Qiaoyun Liu, Yaoyao Ding, Hongyan Liu, Zeling Xu, Yuntao Zou (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13542102.txt.
Description
Qiaoyun Liu and colleagues propose a text classifier in a 2026 study. The tool sorts agricultural news with large language models. It needs no labelled training examples. Farm vocabulary is sparse, and annotation is scarce. Single-prompt methods judge from one angle only. That weakness drives the design.
The framework builds several prompts for each text. Each prompt views the text at a different level. Levels run from local terms to overall theme. A consistency check then compares decisions and confidence scores. Disputed items go to a second judgement round. Tests used French pest reports and a humanitarian news set. Accuracy beat the strongest rival by several points.
Catalog record
| CREATOR | Qiaoyun Liu, Yaoyao Ding, Hongyan Liu, Zeling Xu, Yuntao Zou |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 77262 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |